% When entering into this citation database please: % % - Check whether the entry you are putting in already exists % - Remember that multiple authors MUST have 'and' between them. % Otherwise BibTeX/InterBib will not understand that they're % looking at multiple names. % - Please don't use 'et al'. Put in all the authors. % - If you have a URL for the paper you're entering, please include % a 'links' field in the paper's entry. Just copy an existing one % and modify the URL. This will cause InterBib to link the title % of the paper to that URL when building an HTML % bibliography. Extremely nice. % - Check whether any of the string macros below are applicable. % and use them. For instance: cacm, icde98, ieeecomp, sigir96, % dl98, etc. If one in a series is missing (e.g. vldb99), just add % a macro by copying the previous one in the series. %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% % String Macros %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @string{plieeecs = "IEEE Computer Society, Washington, D.C."} @string{placm = "ACM Press, New York"} @string{plspringer = "Springer, Berlin"} @string{plvldb = "VLDB Endowment, Saratoga, Calif."} @string{plaaai = "AAAI Press, Menlo Park, Calif."} @string{csurvey = "ACM Computing Surveys"} @string{ieeecomp = "IEEE Computer"} @string{tods = "Transactions on Database Systems"} @string{cacm = "Communications of the ACM"} @string{acm = "Association of Computing Machinery"} @string{chi85 = "Proceedings of the Conference on Human Factors in Computing Systems CHI'85"} @string{chi86 = "Proceedings of the Conference on Human Factors in Computing Systems CHI'86"} @string{chi87 = "Proceedings of the Conference on Human Factors in Computing Systems and Graphics Interface, CHI+GI'87"} @string{chi88 = "Proceedings of the Conference on Human Factors in Computing Systems CHI'88"} @string{chi89 = "Proceedings of the Conference on Human Factors in Computing Systems CHI'89"} @string{chi90 = "Proceedings of the Conference on Human Factors in Computing Systems CHI'90"} @string{chi91 = "Proceedings of the Conference on Human Factors in Computing Systems CHI'91"} @string{chi92 = "Proceedings of the Conference on Human Factors in Computing Systems CHI'92"} @string{chi95 = "Proceedings of the Conference on Human Factors in Computing Systems CHI'95"} @string{chi96 = "Proceedings of the Conference on Human Factors in Computing Systems CHI'96"} @string{chi97 = "Proceedings of the Conference on Human Factors in Computing Systems CHI'97"} @string{chi98 = "Proceedings of the Conference on Human Factors in Computing Systems CHI'98"} @string{chi99 = "Proceedings of the Conference on Human Factors in Computing Systems CHI'99"} @string{chi00 = "Proceedings of the Conference on Human Factors in Computing Systems CHI'00"} @string{chi01 = "Proceedings of the Conference on Human Factors in Computing Systems CHI'01"} @string{chi03 = "Proceedings of the Conference on Human Factors in Computing Systems CHI'03"} @string{chi04 = "Proceedings of the Conference on Human Factors in Computing Systems CHI'04"} @string{closws88 = "Proceedings of the First CLOS Users and Implementors Workshop"} @string{closws89 = "Proceedings of the Second CLOS Users and Implementors Workshop"} @string{cois90 = "Proceedings of the Conference on Office Information Systems"} @string{cplusplus90 = "Proceedings of the 1990 Usenix C++ Conference"} @string{cscw86 = "Proceedings of the Conference on Computer-Supported Cooperative Work, CSCW'86"} @string{cscw88 = "Proceedings of the Conference on Computer-Supported Cooperative Work, CSCW'88"} @string{cscw90 = "Proceedings of the Conference on Computer-Supported Cooperative Work, CSCW'90"} @string{cscw92 = "Proceedings of the Conference on Computer-Supported Cooperative Work, CSCW'92"} @string{cscw94 = "Proceedings of the Conference on Computer-Supported Cooperative Work, CSCW'94"} @string{cscw98 = "Proceedings of the Conference on Computer-Supported Cooperative Work, CSCW'98"} @string{dcs87 = "Proceedings of the Seventh International Conference on Distributed Computing Systems"} % ACM DL Proceedings: - note the name changes since DL 96. --kevin @string{dl94 = "Proceedings of the First Annual Conference on the Theory and Practice of Digital Libraries"} @string{dl95 = "Proceedings of the Second Annual Conference on the Theory and Practice of Digital Libraries"} @string{dl96 = "Proceedings of the First ACM International Conference on Digital Libraries"} @string{dl97 = "Proceedings of the Second ACM International Conference on Digital Libraries"} @string{dl98 = "Proceedings of the Third ACM International Conference on Digital Libraries"} @string{dl99 = "Proceedings of the Fourth ACM International Conference on Digital Libraries"} @string{dl00 = "Proceedings of the Fifth ACM International Conference on Digital Libraries"} @string{jcdl01 = "Proceedings of the First ACM/IEEE-CS Joint Conference on Digital Libraries"} @string{jcdl02 = "Proceedings of the Second ACM/IEEE-CS Joint Conference on Digital Libraries"} @string{jcdl03 = "Proceedings of the Third ACM/IEEE-CS Joint Conference on Digital Libraries"} @string{jcdl04 = "Proceedings of the Fourth ACM/IEEE-CS Joint Conference on Digital Libraries"} @string{jcdl05 = "Proceedings of the Fifth ACM/IEEE-CS Joint Conference on Digital Libraries"} @string{edbt94 = "Proceedings of the Fourth Internationl Conference on Extending Database Technology--EDBT'94"} @string{edbt98 = "Proceedings of the Sixth International Conference on Extending Database Technology--EDBT'98"} @string{ecoop87 = "Proceedings of the European Conference on Object-Oriented Programming"} @string{ecoop88 = "Proceedings of the European Conference on Object-Oriented Programming"} @string{ecoop89 = "Proceedings of the European Conference on Object-Oriented Programming"} @string{esa02 = "Proceedings of the 10th European Symposium on Algorithms"} @string{euug87 = "Proceedings of the EUUG Spring 1987 Conference"} @string{hics91 = "Proceedings of the Twenty-Fourth Annual Hawaii International Conference on System Sciences"} @string{ht87 = "Hypertext '87 Proceedings"} @string{ht89 = "Hypertext '89 Proceedings"} @string{icde84 = "Proceedings of the International Conference on Data Engineering"} @string{icde87 = "Proceedings of the Third International Conference on Data Engineering"} @string{icde88 = "Proceedings of the Fourth International Conference on Data Engineering"} @string{icde89 = "Proceedings of the Fifth International Conference on Data Engineering"} @string{icde90 = "Proceedings of the Sixth International Conference on Data Engineering"} @string{icde91 = "Proceedings of the Seventh International Conference on Data Engineering"} @string{icde92 = "Proceedings of the Eighth International Conference on Data Engineering"} @string{icde93 = "Proceedings of the Ninth International Conference on Data Engineering"} @string{icde94 = "Proceedings of the Tenth International Conference on Data Engineering"} @string{icde95 = "Proceedings of the Eleventh International Conference on Data Engineering"} @string{icde96 = "Proceedings of the 12th International Conference on Data Engineering"} @string{icde98 = "Proceedings of the Fourteenth International Conference on Data Engineering"} @string{icde99 = "Proceedings of the 15th International Conference on Data Engineering"} @string{icde00 = "Proceedings of the 16th International Conference on Data Engineering"} @string{ieeetose = "IEEE Transactions on Software Engineering"} @string{ifip8.4-90 = "Proceedings of the IFIP TC8 / WG8.4 Conference on Multi- User Interfaces and Applications"} @string{ijmms = "International Journal of Man-Machine Studies"} @string{jasis = "Journal of the American Society for Information Science"} @string{oods86 = "Proceedings of the International Workshop on Object-Oriented Database Systems"} @string{oopsla86 = "Proceedings of the Conference on Object-Oriented Programming Systems, Languages and Applications"} @string{oopsla87 = "Proceedings of the Conference on Object-Oriented Programming Systems, Languages and Applications"} @string{oopsla88 = "Proceedings of the Conference on Object-Oriented Programming Systems, Languages and Applications"} @string{oopsla89 = "Proceedings of the Conference on Object-Oriented Programming Systems, Languages and Applications"} @string{oopsla90 = "Proceedings of the Conference on Object-Oriented Programming Systems, Languages and Applications"} @string{oopsla91 = "Proceedings of the Conference on Object-Oriented Programming Systems, Languages and Applications"} @string{pdis93 = "Proceedings of 2nd International Conference on Parallel and Distributed Information Systems"} @string{pdis96 = "Proceedings of 4th International Conference on Parallel and Distributed Information Systems"} @string{practsoft = "Proceedings of the ACM SIGSOFT/SIGPLAN Software Engineering Symposium on Practical Software Development Environments"} @string{scamc89 = "Proceedings of the Thirteenth Symposium on Computer Applications in Medical Care"} @string{sigir86 = "Proceedings of the Ninth International Conference on Research and Development in Information Retrieval"} @string{sigir88 = "Proceedings of the Eleventh International Conference on Research and Development in Information Retrieval"} @string{sigir90 = "Proceedings of the Thirteenth International Conference on Research and Development in Information Retrieval"} @string{sigir92 = "Proceedings of the Fifteenth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval"} @string{sigir93 = "Proceedings of the Sixteenth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval"} @string{sigir94 = "Proceedings of the Seventeenth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval"} @string{sigir95 = "Proceedings of the 18th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval"} @string{sigir96 = "Proceedings of the Nineteenth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval"} @string{sigir97 = "Proceedings of the Twentieth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval"} @string{sigir98 = "Proceedings of the Twenty-First Annual International ACM SIGIR Conference on Research and Development in Information Retrieval"} @string{sigir99 = "Proceedings of the Twenty-Second Annual International ACM SIGIR Conference on Research and Development in Information Retrieval"} @string{sigir00 = "Proceedings of the Twenty-Third Annual International ACM SIGIR Conference on Research and Development in Information Retrieval"} @string{sigir03 = "Proceedings of the Twenty-Sixth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval"} @string{sigmod87 = "Proceedings of the {ACM} {S}pecial {I}nterest {G}roup on Management of Data"} @string{sigmod89 = "Proceedings of the International Conference on Management of Data"} @string{sigmod93 = "Proceedings of the International Conference on Management of Data"} @string{sigmod94 = "Proceedings of the International Conference on Management of Data"} @string{sigmod97 = "Proceedings of the International Conference on Management of Data"} @string{sigmod98 = "Proceedings of the International Conference on Management of Data"} @string{sigmod99 = "Proceedings of the International Conference on Management of Data"} @string{sigmod00 = "Proceedings of the International Conference on Management of Data"} @string{tois = "ACM Transactions on Information Systems"} @string{tranos = "ACM Transactions on Office Information Systems"} @string{toit = "ACM Transactions on Internet Technology"} @string{usenix89 = "Proceedings of the 1989 Winter USENIX Technical Conference"} @string{vldbj = "VLDB Journal"} @string{vldb80 = "Proceedings of the Sixth International Conference on Very Large Databases"} @string{vldb85 = "Proceedings of the Eleventh International Conference on Very Large Databases"} @string{vldb87 = "Proceedings of the Thirteenth International Conference on Very Large Databases"} @string{vldb88 = "Proceedings of the Fourteenth International Conference on Very Large Databases"} @string{vldb89 = "Proceedings of the Fifteenth International Conference on Very Large Databases"} @string{vldb90 = "Proceedings of the Sixteenth International Conference on Very Large Databases"} @string{vldb91 = "Proceedings of the Seventeenth International Conference on Very Large Databases"} @string{vldb92 = "Proceedings of the Eighteenth International Conference on Very Large Databases"} @string{vldb93 = "Proceedings of the Nineteenth International Conference on Very Large Databases"} @string{vldb94 = "Proceedings of the Twentieth Internationl Conference on Very Large Databases"} @string{vldb95 = "Proceedings of the Twenty-first International Conference on Very Large Databases"} @string{vldb96 = "Proceedings of the Twenty-second International Conference on Very Large Databases"} @string{vldb97 = "Proceedings of the Twenty-third International Conference on Very Large Databases"} @string{vldb98 = "Proceedings of the Twenty-fourth International Conference on Very Large Databases"} @string{vldb99 = "Proceedings of the Twenty-fifth International Conference on Very Large Databases"} @string{vldb00 = "Proceedings of the Twenty-sixth International Conference on Very Large Databases"} @string{vldb01 = "Proceedings of the Twenty-seventh International Conference on Very Large Databases"} @string{www94 = "Proceedings of the Second International World-Wide Web Conference"} @string{www95 = "Proceedings of the Fourth International World-Wide Web Conference"} @string{www96 = "Proceedings of the Fifth International World-Wide Web Conference"} @string{www97 = "Proceedings of the Sixth International World-Wide Web Conference"} @string{www98 = "Proceedings of the Seventh International World-Wide Web Conference"} @string{www99 = "Proceedings of the Eighth International World-Wide Web Conference"} @string{www00 = "Proceedings of the Ninth International World-Wide Web Conference"} @string{www01 = "Proceedings of the Tenth International World-Wide Web Conference"} @string{www04 = "Proceedings of the Thirteenth International World-Wide Web Conference"} @string{icdt97 = "Proceedings of the 6th International Conference on Database Theory"} @string{icdt03 = "Proceedings of the 9th International Conference on Database Theory"} @string{pods96 = "Proceedings of the 15th ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems"} @string{pods95 = "Proceedings of the 14th ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems"} @string{pods94 = "Proceedings of the 13rd ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems"} @string{pods93 = "Proceedings of the 12th ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems"} @string{tpds = "IEEE Transactions on Parallel and Distributed Systems"} @string{jacm = "Journal of the ACM"} @string{mm03 = "Proceedings of the 11th International Conference on Multimedia ({MM}2003)"} @string{mm04 = "Proceedings of the 12th International Conference on Multimedia ({MM}2004)"} %------------------------------------ @INPROCEEDINGS{hamm97 ,AUTHOR = "Joachim Hammer and Hector Garcia-Molina and Junghoo Cho and Arturo Crespo and Rohan Aranha" ,TITLE = "Extracting Semistructured Information from the Web" ,BOOKTITLE = "Proceedings of the Workshop on Management of Semistructured Data" ,YEAR = "1997" ,entered-by = "Steven Ketchpel" ,abstract = {~} } @INPROCEEDINGS{cgm97 ,AUTHOR = "Edward Chang and Hector Garcia-Molina" ,TITLE = "Reducing Initial Latency in Media Servers" ,BOOKTITLE = "IEEE Multimedia" ,YEAR = "1997" ,volume = "4" ,number = "3" ,entered-by = "Steven Ketchpel" ,abstract = {~} } @INPROCEEDINGS{cgm97a ,AUTHOR = "Edward Chang and Hector Garcia-Molina" ,TITLE = "Effective Memory Use in a Media Server" ,BOOKTITLE = "Proceedings of the 23rd Very Large Data Base (VLDB) Conference" ,YEAR = "1997" ,entered-by = "Steven Ketchpel" ,abstract = {~} } @INPROCEEDINGS{bks97 ,AUTHOR = "E. Bauer and D. Koller and Y. Singer" ,TITLE = "Update Rules for parameter estimation in {B}ayesian networks" ,BOOKTITLE = "Proceedings of the 13th Annual Conference on Uncertainty in AI (UAI)" ,YEAR = "1997" ,entered-by = "Steven Ketchpel" ,abstract = {~} } @INPROCEEDINGS{gmks98 ,AUTHOR = "Hector Garcia-Molina and Steven Ketchpel and Narayanan Shivakumar" ,TITLE = "Safeguarding and Charging for Information on the {I}nternet" ,BOOKTITLE = icde98 ,YEAR = "1998" ,note = "Available at http://dbpubs.stanford.edu/pub/1998-26" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1998-26)" ,entered-by = "Steven Ketchpel" } @ARTICLE{kgm97 ,AUTHOR = "Steven Ketchpel and Hector Garcia-Molina" ,TITLE = "A Sound and Complete Algorithm for Distributed Commerce Transactions" ,JOURNAL = "Distributed Computing" ,YEAR = "1999" ,volume = "12" ,number = "1" ,note = "Available at http://dbpubs.stanford.edu/pub/2000-44" ,entered-by = "Steven Ketchpel" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-44)" ,abstract = {In a multi-party transaction such as fulfilling an information request from multiple sources (also called a distributed commerce transaction), agents face risks from dealing with untrusted agents. These risks are compounded in the face of deadlines, e.g., an agent may fail to deliver purchased goods by the time the goods are needed. We present a distributed algortihm that mitigates these risks, by generating a safe sequence of actions (when possible) that completes a commerce transaction with no risk. We show that the algorithm is sound (produces only safe multi-agent action sequences) and complete (finds a safe sequence whenever one exists). We also show how the algorithm may be extended so that agents may interact directly with other participants rather than through a trusted intermediary. } } @INPROCEEDINGS{kgm98a ,AUTHOR = "Steven Ketchpel and Hector Garcia-Molina" ,TITLE = "Competitive Sourcing for Internet Commerce" ,BOOKTITLE = "Proceedings of International Conference on Distributed Computing Systems" ,YEAR = "1998" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1998-58)" ,entered-by = "Steven Ketchpel" ,abstract = {Abstract: In electronic commerce on the Internet, a customer can choose among several competitive suppliers, but because of the nature of the Internet, the reliability and trustworthiness of suppliers may vary significantly. The customer's goal is to maximize its utility, by minimizing the expense required to fulfill its request, and maximizing its probability of success by some deadline. To this end, the customer creates a request strategy, describing which suppliers to contact under what conditions. In this paper we describe models for representing request strategies complete with supplier reliabilities, delivery timeliness profiles, and customer deadlines. We also develop decision procedures for selecting request strategies that maximize expected utility under certain scenarios, and more efficient heuristics that approximate the optimal solution.} } @INPROCEEDINGS{bs95 ,AUTHOR = "Marko Balabanovic and Yoav Shoham" ,TITLE = "Learning Inforamtion Retrieval Agents: Experiments with Automated Web Browsing" ,BOOKTITLE = "Proceedings of the AAAI Spring Symposium on Information Gathering from Heterogenous, Distributed Resources" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/balabanovic.ps.Z)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript} } @ARTICLE{bala95a ,AUTHOR = "M. Balabanovic and Y. Shoham and Y. Yun" ,TITLE = "An Adaptive Agent for Automated Web Browsing" ,JOURNAL = "Journal of Visual Communication and Image Representation" ,YEAR = "1995" ,month = "December" ,volume = "6" ,number = "4" ,notes = "(Special issue on Digital Libraries)" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @TECHREPORT{bald95 ,AUTHOR = "Michelle Q Wang Baldonado and Terry Winograd" ,TITLE = "Techniques and Tools for Making Sense out of Heterogeneous Search Service Results" ,INSTITUTION = "Stanford University" ,YEAR = "1995" ,number = "SIDL-WP-1995-0019; 1995-59" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1995-59)" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @TECHREPORT{bald96 ,AUTHOR = "Michelle Q Wang Baldonado and Terry Winograd" ,TITLE = "A User Interaction Model for Browsing Based on Category-Level Operations" ,INSTITUTION = "Stanford University" ,YEAR = "1996" ,number = "SIDL-WP-1996-0029; 1996-75" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1996-75)" ,entered-by = "Andreas Paepcke" ,abstract = {We propose a user interaction model for browsing based on itera tive category-level operations. The motivation comes from two observations: 1) people naturally think in terms of categories, and 2) in browsing, the types of categories that are salient to users change as they browse. We define a set of category-level operations that lets users iteratively view and find results in terms of these changing category types. We also show that we can express some standard IR operations as iteratively applied sequences of a funda mental category-level operation (thus unifying them). Finally, we describe SenseMaker, a prototype interface for browsing heteroge neous sources.} } @INPROCEEDINGS{chan96 ,AUTHOR = "Edward Chang and H\'ector Garc\'{\i}a-Molina" ,TITLE = "Reducing Initial Latency in a Multimedia Storage System" ,BOOKTITLE = "Third International Workshop of Multimedia Database Systems" ,YEAR = "1996" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1996-65)" ,entered-by = "Andreas Paepcke" ,abstract = {A multimedia server delivers presentations (e.g., videos, movies, providing high bandwidth and continuous real-time deliveryIn this paper we present techniques for reducing the initial latency of presentations, i.e., for reducing the time between the arrival of a request and the start of the presentation. Traditionally, initial latency has not received much attention. This is because one major application of multimedia servers is movies on demand where a delay of a few minutes before a new multi-hour movie starts is acceptable. However , latency reduction is important in interactive applications such as video games and browsing of multimedia documents. V arious latency reduction schemes are proposed and analyzed, and their performance compared. We show that our techniques can signicantly reduce (almost eliminate in some cases) initial latency without adversely affecting throughput. Moreover , a novel on-disk partial data replication scheme that we propose proves to be far more cost effective than any other previous attempts at reducing initial latency. Keywords: multimedia, data placement, data replication.} } @ARTICLE{chan96a ,AUTHOR = "Chen-Chuan K. Chang and H\'ector Garc\'{\i}a-Molina and Andreas Paepcke" ,TITLE = "Boolean Query Mapping Across Heterogeneous Information Sources" ,JOURNAL = "IEEE Transactions on Knowledge and Data Engineering" ,YEAR = "1996" ,month = {Aug} ,volume = "8" ,number = "4" ,pages = "515-521" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1997-66)" ,entered-by = "Andreas Paepcke" ,keywords = "Boolean queries, query translation, information retrieval, heterogeneity, digital libraries, query subsumption, filtering." ,abstract = {Very technical, formal description of query translation. But has the architecture picture.} } @TechReport{chan96a-e ,author = {Chen-Chuan K. Chang and H\'ector Garc\'{\i}a-Molina and Andreas Paepcke} ,title = {Boolean Query Mapping Across Heterogeneous Information Sources (Extended Version)} ,institution = {Dept. of Computer Science, Stanford Univ.} ,year = 1996 ,number = {SIDL-WP-1996-0044; 1996-1} ,note = {Accessible at http://dbpubs.stanford.edu/pub/1996-1)} ,links = "(title:www:http://dbpubs.stanford.edu/pub/1996-1)" ,address = {Stanford, California} ,keywords = "Boolean queries, query translation, information retrieval, heterogeneity, digital libraries, query subsumption, filtering." ,month = {Sep} ,abstract = {Extend version of the paper of the same title appeared in TKDE Aug. 1996} } @ARTICLE{chan99 ,AUTHOR = "Chen-Chuan K. Chang and H\'ector Garc\'{\i}a-Molina and Andreas Paepcke" ,TITLE = "Predicate Rewriting for Translating Boolean Queries in a Heterogeneous Information System" ,JOURNAL = tois ,YEAR = "1999" ,month = "January" ,volume = "17" ,number = "1" ,pages = "1-39" ,note = "Available at http://dbpubs.stanford.edu/pub/1999-34" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1999-34)" ,entered-by = "Andreas Paepcke" ,keywords = "query translation, interoperability" ,abstract = {Searching over heterogeneous information sources is difficult in part because of the nonuniform query languages. Our approach is to allow users to compose Boolean queries in one rich front-end language. For each user query and target source, we transform the user query into a subsuming query that can be supported by the source but that may return extra documents. The results are then processed by a filter query to yield the correct final results. In this article we introduce the architecture and associated mechanism for query translation. In particular, we discuss techniques for rewriting predicates in Boolean queries into native subsuming forms, which is a basis of translating complex queries. In addition, we present experimental results for evaluating the cost of postfiltering. We also discuss the drawbacks of this approach and cases when it may not be effective. We have implemented prototype versions of these mechanisms and demonstrated them on heterogeneous Boolean systems.} } @INPROCEEDINGS{ckp+95 ,AUTHOR = " Steve B. Cousins and Steven P. Ketchpel and Andreas Paepcke and H\'ector Garc\'{\i}a-Molina and Scott W. Hassan and Martin Roescheisen" ,TITLE = " InterPay: Managing Multiple Payment Mechanisms in Digital Libraries" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/cousins/cousins.html)" ,ABSTRACT = {Format: HTML Document(39K + pictures) . Audience: Computer Scientists. References: 10. Links: 8. Relevance: High. Abstract: Describes an architecture called InterPay for allowing heterogeneous payment mechanisms to interoperate. Defines three levels (a task level, payment policy level, and payment mechanism level) that may be modified in dependently. Describes a working prototype using the ILU distributed object system from Xerox. Shows a sample transaction using the architecture, and how the components of the architecture (payment agents, collection agents, and paym ent and collection capabilities) can be used in more complex transactions. } } @TECHREPORT{cous96a ,AUTHOR = "Steve B. Cousins and Scott W. Hassan and Andreas Paepcke and Terry Winograd" ,TITLE = "Towards Wide-Area Distributed Interfaces" ,INSTITUTION = "Stanford University" ,YEAR = "1996" ,number = "SIDL-WP-1996-0037; 1997-67" ,note = "Available at http://dbpubs.stanford.edu/pub/1997-67" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1997-67)" ,entered-by = "Andreas Paepcke" ,keywords = "DLITE, distributed interfaces" ,abstract = {Describes how the DLITE design enables shifting of functionality among distributed components.} } @INPROCEEDINGS{cous96c ,AUTHOR = "Steve B. Cousins and Andreas Paepcke and Terry Winograd and Eric A. Bier and Ken Pier" ,title = "The Digital Library Integrated Task Environment (DLITE)" ,YEAR = "1997" ,BOOKTITLE = dl97 ,pages = "142--151" ,note = "Accessible at http://dbpubs.stanford.edu/pub/1997-69" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1997-69)" ,entered-by = "Andreas Paepcke" ,keywords = "dlite" ,abstract = {~} } @MANUAL{cutt93a ,TITLE = "{ILU} Reference Manual" ,author = "Doug Cutting and Bill Janssen and Mike Spreitzer and Farrell Wymore" ,organization = "Xerox Palo Alto Research Center" ,note = "Accessible at {\tt ftp://\-ftp.parc.xerox.com/\-pub/\-ilu/\- ilu.html}" ,month = "December " ,year = "1993" ,links = "(title:www:ftp://ftp.parc.xerox.com/pub/ilu/ilu.html)" ,entered-by = "Andreas Paepcke" ,keywords = "ILU, distributed objects, digital library" ,abstract = {Reference manual. Tech report at cour94} } @INPROCEEDINGS{cres96 ,AUTHOR = "Arturo Crespo and Eric A. Bier" ,TITLE = "Web{W}riter: A Browser-Based Editor for Constructing Web Applications" ,BOOKTITLE = www96 ,YEAR = "1996" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1996-6)" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @INPROCEEDINGS{grav95 ,AUTHOR = "Luis Gravano and H\'ector Garc\'{\i}a-Molina" ,TITLE = "Generalizing {{\em GlOSS\/}} to Vector-Space Databases and Broker Hierarchies" ,BOOKTITLE = vldb95 ,YEAR = "1995" ,MONTH = Sep ,PAGES = "78--89" ,entered-by = "Andreas Paepcke" ,links = "(title:www:http://dbpubs.stanford.edu/pubs/1999-63)" ,links = "(title:www:http://www-db.stanford.edu/pub/gravano/1995/vldb95.ps)" ,abstract = {~} } @INPROCEEDINGS{grav97 ,AUTHOR = "Luis Gravano and Hector Garcia-Molina" ,TITLE = "Merging Ranks from Heterogeneous Internet Sources" ,BOOKTITLE = vldb97 ,YEAR = "1997" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-41)" ,entered-by = "Andreas Paepcke" ,keywords = "GlOSS" ,abstract = {~} } @INPROCEEDINGS{ketc95 ,AUTHOR = "Steven Ketchpel" ,TITLE = "Transaction Protection for Information Buyers and Sellers" ,BOOKTITLE = "DAGS '95" ,YEAR = "1995" ,LINKS = "(title:www:http://robotics.stanford.edu/users/ketchpel/dags4.html)" ,ABSTRACT = {Format: HTML Document (28K) . Audience: Computer scientists. References: 6. Links: 7. Relevance: High. Abstract: Describes protocols and mechanisms which allow parties in an information sale to ensure that neither side is taken advantage of. (eg, giving information without getting paid, or paying without getting promised inform ation) Uses digital signatures to verify the source, relies on a trusted intermediary to act as either a delivery service or escrow agent (which determines whether it works to prevent problems or just punish people who commit them.). } } @INPROCEEDINGS{ketc96 ,AUTHOR = "Steven Ketchpel and H\'ector Garc\'{\i}a-Molina" ,TITLE = "Making Trust Explicit in Distributed Commerce Transactions" ,BOOKTITLE = "Proceedings of the International Conference on Distributed Computing Systems" ,YEAR = "1996" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1995-58)" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @MISC{koll96 ,author = "Daphne Koller and Mehran Sahami" ,title = "Toward Optimal Feature Selection" ,year = "1996" ,howpublished = "Submitted for publication" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @MISC{lync95 ,author = "Clifford Lynch and H\'ector Garc\'{\i}a-Molina" ,title = "IITA Digital Libraries Workshop Report." ,year = "1995" ,month = "May" ,howpublished = "Available on request" ,address = "Marianne Siroker, Stanford University, GATES 436, Stanford, CA. 94305" ,entered-by = "Andreas Paepcke" ,links = "(title:www:http://www-diglib.stanford.edu/diglib/pub/reports/iita- dlw/main.html)" ,abstract = {~} } @ARTICLE{paep96a ,AUTHOR = {Andreas Paepcke and Steve B. Cousins and H\'ector Garc\'{\i}a- Molina and Scott W. Hassan and Steven K. Ketchpel and Martin R\"{o}scheisen and Terry Winograd} ,TITLE = "Using Distributed Objects for Digital Library Interoperability" ,JOURNAL = "IEEE Computer Magazine" ,YEAR = "1996" ,month = "May" ,volume = "29" ,number = "5" ,pages = "61--68" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1998-57)" ,entered-by = "Andreas Paepcke" ,keywords = "infobus" ,abstract = {Standard citation for InfoBus} } @TECHREPORT{rmw94 ,AUTHOR = "Martin R{\"{o}}scheisen and Christian Mogensen and Terry Winograd" ,TITLE = "Shared Web Annotations As A Platform for Third-Party Value-Added Information Providers: Architecture, Protocols, and Usage Examples" ,INSTITUTION = "Computer Science Department, Stanford University" ,YEAR = "1994" ,month = "Nov" ,links = "(title:www:http://www-pcd.stanford.edu/COMMENTOR/)" ,entered-by = "Steven Ketchpel" ,abstract = {~} } @INPROCEEDINGS{rosc95 ,AUTHOR = "M. R{\"{o}}scheisen and C. Mogensen and T. Winograd" ,TITLE = "Interaction Design for Shared World-Wide Web Annotations" ,BOOKTITLE = chi95 ,YEAR = "1995" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @INPROCEEDINGS{rosc95a ,AUTHOR = "M. R{\"{o}}scheisen and C. Mogensen and T. Winograd" ,TITLE = "Beyond Browsing: Shared Comments, {SOAP}s, Trails and On-line Communities" ,BOOKTITLE = www95 ,YEAR = "1995" ,pages = "739-749" ,address = "Darmstadt, Germany" ,entered-by = "Andreas Paepcke" ,abstract = {The paper describes a system we have implemented that enables people to share structured in-place annotations attached to material in arbitrary documents on the WWW. The basic conceptual decisions are laid out, and a prototypical example of the client server interaction is given. We then explain the usage perspective, describe our experience with using the system, and discuss other experimental usages of our prototype implementation, such as collaborative filtering, seals of approval, and value added trails. We show how this is a specific instantiation of a more general "virtual document" architecture in which, with the help of light weight distributed meta information, viewed documents can incorporate material that is dynamically integrated from multiple distributed sources. Development of that architecture is part of a larger project on Digital Libraries that we are engaged in } } @ARTICLE{rosc95b ,AUTHOR = "Martin R{\"{o}}scheisen and Terry Winograd and Andreas Paepcke" ,TITLE = "Content Ratings and Other Third-Party Value-Added Information: Defining an Enabling Platform" ,JOURNAL = "CNRI D-Lib Magazine" ,YEAR = "1995" ,month = "August" ,links = "(title:www:http://www.dlib.org/dlib/august95/stanford/roscheisen.html)" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @TECHREPORT{rosc95c ,AUTHOR = "M. R{\"{o}}scheisen and C. Mogensen and T. Winograd" ,TITLE = "A Platform for Third-Party Value-Added Information Providers: Architecture, Protocols, and Usage Examples" ,INSTITUTION = "Stanford University" ,YEAR = "1995" ,month = "May" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @ARTICLE{rosc97 ,AUTHOR = "Martin R{\"{o}}scheisen and Terry Winograd" ,TITLE = "A Network-Centric Design for Relationship-Based Rights Management" ,JOURNAL = "Journal of Computer Security" ,volume = 5 ,number = 3 ,pages = "249--254" ,YEAR = "1997" ,note = "Available at http://dbpubs.stanford.edu/pub/2000-46. The author's dissertation with the same title was completed at Stanford University." ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-46)" ,entered-by = "Andreas Paepcke" ,abstract = {Main article for Roscheisen's work on the use of contract notions for digital library rights management.} } @INPROCEEDINGS{rw96 ,AUTHOR = "Martin R{\"{o}}scheisen and Terry Winograd" ,TITLE = "A Communication Agreement Framework of Access/Action Control" ,BOOKTITLE = "Proceedings of the 1996 IEEE Symposium on Research in Security and Privacy" ,YEAR = "1996" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1996-74)" ,entered-by = "Steven Ketchpel" ,keywords = "Compacts, authorization, security" ,abstract = {Format: PostScript (286K)} } @ARTICLE{shiv95 ,AUTHOR = "N. Shivakumar and H. Garcia-Molina" ,TITLE = "The SCAM Approach to Copy Detection in Digital Libraries" ,JOURNAL = "CNRI D-Lib Magazine" ,YEAR = "1995" ,month = "November" ,links = "title:www:http://www.dlib.org/dlib/november95/scam/11shivakumar.html" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @MISC{sidl95 ,title = "The {S}tanford {D}igital {L}ibrary {P}roject" ,year = "1995" ,howpublished = "Special Issue of the Communications of the ACM" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @INPROCEEDINGS{yan96 ,AUTHOR = "Tak Woon Yan and Matthew Jacobsen and H\'ector Garc\'{\i}a-Molina and Umeshwar Dayal" ,TITLE = "From User Access Patterns to Dynamic Hypertext Linking" ,BOOKTITLE = www96 ,YEAR = "1996" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1996-76)" ,entered-by = "Andreas Paepcke" ,keywords = "value filtering" ,abstract = {This paper describes an approach for automatically classifying visitors of a web site according to their access patterns. User access logs are examined to discover clusters of users that exhibit similar information needs; e.g., users that access similar pages. This may result in a better understanding of how users visit the site, and lead to an improved organization of the hypertext documents for navigational convenience. More interestingly, based on what categories an individual user falls into, we can dynamically suggest links for him to navigate. In this paper, we describe the overall design of a system that implements these ideas, and elaborate on the preprocessing, clustering, and dynamic link suggestion tasks. We present some experimental results generated by analyzing the access log of a web site. } } @INPROCEEDINGS{md94 ,AUTHOR = "Francis Miksa and Philip Doty" ,TITLE = " Intellectual Realities and the Digital Library" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/miksa.html)" ,ABSTRACT = {Format: HTML document (24K) Audience: Non-technical, librarians. References: 4. Links: 1. Relevance: Low. Abstract: Asks how a digital library is a library. Considers different aspects of libraries and to what extent they are matched by a DL. } } @INPROCEEDINGS{mmpr94 ,AUTHOR = "Cliff McKnight and Jack Meadows and David Pullinger and Fytton Rowland" ,TITLE = "ELVYN--Publisher and Library Working Towards the Electronic Distribution and Use of Journals" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/mcknight.html)" ,ABSTRACT = {Format: HTML Document (24K) . Audience: Non-technical, librarians (though some jargon is used). References: 9. Links: 1. Relevance: Low-Medium. Abstract: Describes an existing project of journal distribution to libraries via electronic formats. Claims that libraries & publishers still have a role in the new model. } } @INPROCEEDINGS{lem+94 ,AUTHOR = "Elizabeth D. Liddy and Michael B. Eisenberg and Charles R. McClure and Kim Mills and Susan Mernit and James D. Luckett" ,TITLE = " Research Agenda for the Intelligent Digital Library" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/liddy.html)" ,ABSTRACT = {Format: HTML Document (40K) . Audience: Mostly non-technical, librarians, funders. References: Not included. Links: 1. Relevance: Low-Medium. Abstract: Describes an ambitious project proposal to create a digital librarian to handle natural language requests. Documents understood via TIPSTER-like system. Proposal for implementing parallel, connectionist models of t he NLP module. Also interested in impact of such a system for K-12 education. } } @INPROCEEDINGS{sbmh94 ,AUTHOR = "Bruce Schatz and Ann Bishop and William Mischo and Joseph Hardin" ,TITLE = " Digital Library Infrastructure for a University Engineering Community" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/schatz.html)" ,ABSTRACT = {Format: HTML Document () . Audience: Non-technical, librarians, funders (some jargon). References: Not included. Links: 1. Relevance: Low. Abstract: This proposal describes the DL project at U. of Illinois. It will focus on engineering documents. One idea contained within is searching "concept space" rather than object space, where concepts are a graph of co- occuring terms. } ,privateComment = "Essentially free of technical content" } @INPROCEEDINGS{ssd+94 ,AUTHOR = "David Stotts and John Smith and Prasun Dewan and Kevin Jeffay and F. Donalson Smith and Dana Smith and Steven Weiss and James Coggins and William Oliver" ,TITLE = " A Patterned Injury Digital Library for Collaborative Forensic Medicine" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/stotts.html)" ,ABSTRACT = {Format: HTML Document (44K). Audience: Mostly Non-technical, pathologists, funders . References: 26. Links: 1. Relevance: Low. Abstract: Considers the benefits and research issues related to the construction fo a collection of forensic data (image, video). Short description of some related technologies (WWW, Trellis, Dexter, ABC, Hypersets). } } @INPROCEEDINGS{slh+94 ,AUTHOR = "Sargur N. Srihari and Stephen W. Lam and Jonathan J. Hull and Rohini K. Srihari and Venugopal Govindaraju" ,TITLE = " Intelligent Data Retrieval from Raster Images of Documents" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/srihari.html)" ,ABSTRACT = {Format: HTML Document (24K + pictures) . Audience: Semi-technical, general computer scientists. References: 12. Links: 1. Relevance: Medium (but not mainstream DL). Abstract: Describes a method for getting information from raster image of documents. OCR aided by appealing to word frequencies in similar documents; some processing of graphics (sort by type--bar chart, pie chart, photo, tab le, schematic drawing), builds upon related system to find faces in photos. } } @INPROCEEDINGS{bmw94 ,AUTHOR = "Timothy C. Bell and Alistair Moffat and Ian H. Witten" ,TITLE = " Compressing the Digital Library" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/bell.html)" ,ABSTRACT = {Format: HTML Document (32K) . Audience: Semi-technical, general computer scientists. References: 8. Links: 1. Relevance: Medium (but not mainstream DL). Abstract: Discusses the interaction of compression and indexing. Suggests a Huffman encoding applied to words & non-words. Inverted bitmap for indexing, enhanced with Golomb encoding. Compressed 266 Mb Wall Street Journal a rticle database by 50%+ (even after index was included), in one hour on workstation, including creating the index. Queries were processed in less than .1 sec. } } @INPROCEEDINGS{gae+94 ,AUTHOR = "Susan Gauch and Ron Aust and Joe Evans and John Gauch and Gary Minden and Doug Niehaus and James Roberts" ,TITLE = " The Digital Video Library System: Vision and Design" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/gauch.html)" ,ABSTRACT = {Format: HTML Document (29K) . Audience: slightly technical, generalist comfortable with technology. References: 23. Links: 1. Relevance: Medium-Low (but not mainstream DL). Abstract: Describes architecture of a system to retrieve & deliver video on demand. Indexing done by audio track or transcript. 100 hours of video to 20-30 users. Different compression modes depending on bandwidth of user co nnection. } } @INPROCEEDINGS{bdf+94 ,AUTHOR = "William P. Birmingham and Karen M. Drabenstott and Carolyn O. Frost and Amy J. Warner and Katherine Willis" ,TITLE = " The University of Michigan Digital Library: This is Not Your Father's Library" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/umdl.html)" ,ABSTRACT = {Format: HTML Document (36K) . Audience: slightly technical, generalist comfortable with technology, funders. References: 13. Links: 1. Relevance: Medium-High. Abstract: Describes the UMichigan Digital Libraries proposal, including some detail about their agent architecture. User agents, Collection-interface agents, and mediators all play a role. Network resources are allocated on a market-based mechanism, and proposal mentions need to protect intellectual property & handle payment issues. } } @INPROCEEDINGS{th94 ,AUTHOR = "Richard M. Tong and David H. Holtzman" ,TITLE = " Knowledge-Based Access to Heterogeneous Information Sources" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/tong.html)" ,ABSTRACT = {Format: HTML Document (24K) . Audience: slightly technical, generalist comfortable with technology, funders, slight business slant. References: 4. Links: 1. Relevance: Low-Medium. Abstract: Describes the MINERVA architecture developed at Booz Allen. Two levels of mediators between users and content sources. Describes "Text Reference Language" to describe queries. } } @INPROCEEDINGS{mmd+94 ,AUTHOR = "Kathleen McKeown and David Millman and Brian Donnelly and James Hoover and Robert McClintock and Willem Scholten and Dimitris Anastassiou and Shih-Fu Chang and Alan Croswell and Mukesh Dalal and Steven Feiner and Paul Kantor and Judith Klavans and Mischa Schwartz" ,TITLE = " The JANUS Digital Library" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/janus.html)" ,ABSTRACT = {Format: HTML Document (33K) . Audience: non-technical, funders. References: 26. Links: 1. Relevance: Low-Medium. Abstract: Project description of the JANUS library centered at Columbia. Focuses on user interface, generation of NL summaries, multimedia searching, some intellectual property. } } @INPROCEEDINGS{srm+94 ,AUTHOR = "Ben Shneiderman and Azriel Rosenfeld and Gary Marchionini and William G. Holliday and Glenn Ricart and Christos Faloutsos and Judith P. Dick" ,TITLE = " QUEST--Query Environment for Science Teaching" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/shneiderman.html)" ,ABSTRACT = {Format: HTML Document (31K). Audience: non-technical, funders. References: 14. Links: 1. Relevance: Low-Medium. Abstract: Describes U. of Maryland digital libraries proposal. Focused on user interface, search engines, multimedia, information capture (e.g., page segmentation). In the context of science education. } } @INPROCEEDINGS{fz94 ,AUTHOR = "Robert P. Futrelle and Xiaolan Zhang" ,TITLE = " Large-Scale Persistent Object Systems for Corpus Linguistics and Information Retrieval" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/futrelle.html)" ,ABSTRACT = {Format: HTML Document (40K + picture) . Audience: technical, computer scientists with some knowledge of computational linguistics. References: 31. Links: 1. Relevance: Medium-Low. Abstract: Discusses the challenges in indexing/searching large databases. Argues for a bootstrapping/machine learning approach to locate words in related contexts (surrounding words). Suggests specific data structures. Discusses tradeoffs between accuracy & speed, and scaling problems. } } @INPROCEEDINGS{gk94 ,AUTHOR = "Jos\'{e}-Marie Griffiths and Kimberly K. Kertis." ,TITLE = " Access to Large Digital Libraries of Scientific Information Across Networks" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/tennessee.html)" ,ABSTRACT = {Format: HTML Document (34K) . Audience: slightly technical, funders, general technology. References: 14. Links: 1. Relevance: Low-Medium. Abstract: Describes U. of Tennessee's Digital Library proposal. Focuses on: representation, navigation, retrieval, display of information; performance & scalability; different user interfaces for different user groups. Semantic net concept representation. } } @INPROCEEDINGS{alle94 ,AUTHOR = "Robert B. Allen" ,TITLE = " Navigating and Searching in Hierarchical Digital Library Catalogs" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/allen.html)" ,ABSTRACT = {Format: HTML Document (21K) . Audience: non technical, users. References: 15. Links: 2. Relevance: Low. Abstract: Describes a particular user interface based on a book shelf metaphor. Tries to use an a priori classification (Dewey Decimal System) as an organization tool (in addition to results of electronic searches). } } @INPROCEEDINGS{gfa+94 ,AUTHOR = "Henry M. Gladney and Edward A. Fox and Zahid Ahmed and Ron Ashany and Nicholas J. Belkin and Michael Lesk and Richard Tong and Maria Zemankova" ,TITLE = " Digital Library: Gross Structure and Requirements (Report from a March 1994 Workshop)" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/fox.html)" ,ABSTRACT = {Format: HTML Document (35K) . Audience: DL researchers, workgroup attendees. References: 22. Links: 1. Relevance: Low-Medium. Abstract: The report of a working group on digital libraries. Defines terms, discusses a possible architecture in terms of resource managers and application enablers. } } @INPROCEEDINGS{slm+94 ,AUTHOR = "John L. Schnase and John J. Leggett and Edward S. Metcalfe and Nancy R. Morin and Edward L.Cunnius and Jonathan S. Turner and Richard K. Furuta and Leland Ellis and Michael S. Pilant and Richard E. Ewing and Scott W. Hassan and Mark E. Frisse" ,TITLE = " The CoLib Project--Enabling Digital Botany for the 21st Century" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/colib.html)" ,ABSTRACT = {Format: HTML Document (49K) . Audience: Non-technical, funders, botanists. References: 30. Links: 1. Relevance: Low. Abstract: U. of Missouri's digital libraries proposal, in the botany domain. points: need for collaboration among DL users, ATM as network platform. } } @INPROCEEDINGS{ec94 ,AUTHOR = "Kate Ehrlich and Debra Cash" ,TITLE = " Turning Information into Knowledge: Information Finding as a Collaborative Activity" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/lotus.html)" ,ABSTRACT = {Format: HTML Document (30K) . Audience: Non-technical, social science, "work flow". References: 16. Links: 1. Relevance: Low. Abstract: Case study of customer service organization that uses Lotus Notes. Discusses importance of face-to-face, informal communication, human "information mediators". } } @INPROCEEDINGS{msm94 ,AUTHOR = "Catherine C. Marshall and Frank M. Shipman III and Raymond J. McCall" ,TITLE = " Putting Digital Libraries to Work: Issues from Experience with Community Memories" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/marshall.html)" ,ABSTRACT = {Format: HTML Document (43K + picture) . Audience: Non-technical, Social Scientists, CSCW developers. References: 27. Links: 1. Relevance: Low. Abstract: Discusses the notion of "community memories", how they are created (seeding, evolutionary growth, re-seeding), how they are used & searched. Some specific discussion of particular systems like XNetwork, VIKI, JANUS, NoteCards, VNS. } } @INPROCEEDINGS{kkg+94 ,AUTHOR = "Gary King and H. T. Kung and Barbara Grosz and Sidney Verba and Dale Flecker and Brian Kahin" ,TITLE = " The Harvard Self-Enriching Library Facilities (SELF) Project" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/harvard.html)" ,ABSTRACT = {Format: HTML Document (23K) . Audience: Non technical, funders. References: 0. Links: 1. Relevance: Low-Medium. Abstract: Digital libraries proposal that focuses on 2 way information flow. Allow users to enter annotations, reviews, dataset descriptions, etc. Emphasis on user interface, some intellectual property. Combination of Z39.50 & HTTP. } } @INPROCEEDINGS{furu94 ,AUTHOR = "Richard Furuta" ,TITLE = " Defining and Using Structure in Digital Documents" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/furuta.html)" ,ABSTRACT = {Format: HTML Document (31K) . Audience: Authors, Developers, slightly technical. References: 43. Links: 1. Relevance: Low-Medium. Abstract: Discussion of SGMLs, their motivation, research issues, how they might be extended to non-text objects. Distinction between content & presentation } } @INPROCEEDINGS{ke94 ,AUTHOR = "Rob Kling and Margaret Elliott" ,TITLE = " Digital Library Design for Usability" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/kling.html)" ,ABSTRACT = {Format: HTML Document (49K + picture) . Audience: Non-technical, developers, human factors people. References: 16. Links: 1. Relevance: Low. Abstract: Distinguishes between usability in terms of user interface and "organizational usability" (integration into existing working environment). Claims both are ignored, the latter more so. Presents 5 traditional models of software development (primarily from point of view of end-user inclusion) and a 6th based on organizational usability. } } @INPROCEEDINGS{khl+94 ,AUTHOR = "Charles Kacmar and Susan Hruska and Chris Lacher and Dean Jue and Christie Koontz and Myke Gluck and Stuart Weibel" ,TITLE = " An Architecture and Operation Model for a Spatial Digital Library" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/kacmar.html)" ,ABSTRACT = {Format: HTML Document (32K) . Audience: Mostly non-technical, funders, Geographic IS people. References: 18. Links: 1. Relevance: Low-Medium. Abstract: Discusses value and problems of spatial (geographic) data. Proposes a distributed hierarchy of metadata to assist in location of relevant data. } } @INPROCEEDINGS{lm94 ,AUTHOR = "David M. Levy and Catherine C. Marshall" ,TITLE = " What Color was George Washington's White Horse? A Look at the Assumptions Underlying Digital Libraries" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/levy.html)" ,ABSTRACT = {Format: HTML Document () . Audience: Non technical, digital library researchers. References: 18. Links: 2. Relevance: Medium. Abstract: Raises a number of interesting questions about directions for DL research. Eg, How can DL be integrated with paper documents? What support will there be for collaboration? Where does the DL fall on the permanent, fixed document vs. fluid, short-lived memo spectrum? Description of typical analysts working methods. Problem is not finding relevant information, but determining an appropriate subset to read to solve problem at hand. Much more collaboration than is typical acknowledged. } } @INPROCEEDINGS{bhw94 ,AUTHOR = "Sulin Ba and Aimo Hinkkanen and Andre B. Whinston" ,TITLE = " Digital Library as a Foundation for Decision Support Systems" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/ba.html)" ,ABSTRACT = {Format: HTML Document (43K) . Audience: Semi-technical, business slant, funding proposal. References: 14. Links: 1. Relevance: Low. Abstract: Sees a DL as an enterprise wide collection of *executable* documents. SGML and Mathematica suggested as integration tools. Search for data representation which will allow automatic combination of separate documents to solve problems. } } @INPROCEEDINGS{gsr+94 ,AUTHOR = "R. L. Grossman and A. Sundaram and H. Ramamoorthy and M. Wu and S. Hogan and J. Shuler and O. Wolfson" ,TITLE = " Viewing the U.S. Government Budget as a Digital Library" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/grossman.html)" ,ABSTRACT = { HTML Document (24K) . Audience: Computer scientists, funders . References: 7. Links: 1. Relevance: low. Abstract: Describes a prototype system built using tools to access data from the federal budget. Argues that statistical, numerical data is fundamentally different from text and multimedia. } } @INPROCEEDINGS{rwkr94 ,AUTHOR = "Michael Ribaudo and Colette Wagner and Michael Kress and Bernard Rous" ,TITLE = " The Challenges to Designing Viable Digital Libraries" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/cuny.html)" ,ABSTRACT = {Format: HTML Document (19K) . Audience: Mostly non-technical, funders & business people. References: 5. Links: 1. Relevance: Low-Medium. Abstract: Lists 6 "major" areas that need to be addressed for DL. 1) Is internet sufficient in terms of topology & bandwidth? 2) UI for disabled users? 3) Economic model of publishing 4) Production model for electronic pub lishing (work flow) 5) Electronic tools to support publishing 6) Intellectual Property. Doesn't make concrete suggestions beyond suggesting various committees. } } @INPROCEEDINGS{smw+94 ,AUTHOR = "S. Shen and R. Mukkamala and A. Wadaa and C. Zhang and H. Abdel-Wahab and K. Maly and A. Liu and M. Yuan" ,TITLE = " An Interoperable Architecture for Digital Information Repositories" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/shen.html)" ,ABSTRACT = {Format: HTML Document (29K + Picture) . Audience: Slightly technical, funders. References: 11. Links: 1. Relevance: High. Abstract: Basically a proposal that mirrors the Stanford digital library project. They present a 3 layer architecture (User Interface Layer, Interoperability Layer, Resource Repository Layer) that corresponds closely with the interface clients, InfoBus, and Information Source model. Also includes a brief description of mechanisms for Gopher, WAIS, and Archie. Suggests a protocol using a minimal set of efficient primitives that sources would have to provid e to be part of the library, but also expects the set to be extensible. } } @INPROCEEDINGS{bm94 ,AUTHOR = "Sujata Banerjee and Vibhu O. Mittal" ,TITLE = " On the Use of Linguistic Ontologies for Accessing and Indexing Distributed Digital Libraries" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/paper/banerjee.html)" ,ABSTRACT = {Format: HTML Document () . Audience: Non-technical, on-line searchers. References: 16. Links: 1. Relevance: Low. Abstract: Addresses problem of finding correct keywords to search for by using WordNet. If a search doesn't turn up the hits needed, it modifies query by using synonyms, generalizing, or replacing with a set of more specific words. Searcher is asked to approve modified queries, which are then re-sent to content providers. } } @INPROCEEDINGS{acke94 ,AUTHOR = "Mark S. Ackerman" ,TITLE = " Providing Social Interaction in the Digital Library" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/position/ackerman.html)" ,ABSTRACT = {Format: HTML Document(12K) . Audience: Non-technical, digital library researchers/funders. References: 13. Links: 2. Relevance: Low-medium. Abstract: Argues that social aspects of collaboration must be included in a Digital Library for the informal, organizational things that aren't always available in information sources. Mentions a TCL based system called CAFE that adds functionality of messages, bulletin boards, and talk. } } @INPROCEEDINGS{cg94 ,AUTHOR = "William B. Cavnar and Andrew M. Gillies" ,TITLE = " Data Retrieval and the Realities of Document Conversion" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/position/cavnar.html)" ,ABSTRACT = {Format: HTML Document (9K) . Audience: Semi-technical, general computer science. References: 5. Links: 1. Relevance: Low. Abstract: Discusses need for inexact matching, eg. OCR recognition errors. Proposes using N-grams, overlapping sequences of N adjacent letters as search target. Also research in matching in image of scanned documents (not doing OCR). Some results on mail sorting & census data. } } @INPROCEEDINGS{char94 ,AUTHOR = "Mitchell N. Charity" ,TITLE = " Multiple Standards? No problem" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/position/charity.html)" ,ABSTRACT = {Format: HTML Document (6K) . Audience: Non-technical, standards committee membets. References: 0. Links: 1. Relevance: Medium-low. Abstract: Argues for an IETF rather than ISO model of standards committee. Encouraging several different protocols with gateways being constructed as needed, and generally letting the marketplace determine what survives. } } @INPROCEEDINGS{chk+94 ,AUTHOR = "Francine Chen and Marti Hearst and Julian Kupiec and Jan Pedersen and Lynn Wilcox" ,TITLE = " Mixed-Media Access" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/position/marti.html)" ,ABSTRACT = {Format: HTML Document (8K) . Audience: Researchers, esp. in the area of multi-media searching. References: 8. Links: 1. Relevance: Low-Medium. Abstract: Essentially a set of pointers to Xerox PARC reports. Describes projects related to scatter/gather, automatic segmenting, "keyword" search equivalents for audio & video, and summarization. } } @INPROCEEDINGS{davi94 ,AUTHOR = "Hugh Davis" ,TITLE = " Using Microcosm to Access Digital Libraries" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/position/davis.html)" ,ABSTRACT = {Format: HTML Document (6K) . Audience: UK funders . References: 4. Links: 1. Relevance: Low. Abstract: A description of the Microcosm system (campus document delivery), a hypermedia system allowing links to 3rd party viewers. } } @INPROCEEDINGS{edwa94 ,AUTHOR = "Judith Edwards" ,TITLE = " The Electronic World and Central Queensland University" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/position/edwards.html)" ,ABSTRACT = {Format: HTML Document (6K) . Audience: DL '94 officials & attendees. References: 0 . Links: 1 . Relevance: Low. Abstract: Queensland U's interest in attending DL '94. Some statistics on current and expected use of networked information servers. } } @INPROCEEDINGS{es94 ,AUTHOR = "Mark England Melissa Shaffer" ,TITLE = " Librarians in the Digital Library" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/position/england.html)" ,ABSTRACT = {Format: HTML Document (6K) . Audience: Librarians and Digital Library researchers. References: 0. Links: 1. Relevance: Medium. Abstract: Offers predictions/suggestions for the role of librarians as "teaching, consulting, researching, preserving intellectual and access freedom, and collaborating in the design, application, and maintenance of information access systems." } } @INPROCEEDINGS{furu94b ,AUTHOR = "Kenneth Furuta" ,TITLE = " Librarianship in the Digital Library" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/position/kfuruta.html)" ,ABSTRACT = {Format: HTML Document (4K) . Audience: Librarians and Digital Library researchers. References: 0. Links: 1. Relevance: Low. Abstract: A view on the role in classification, reference, ensuring access, and collection development for the librarian of a digital library. } } @INPROCEEDINGS{klin94 ,AUTHOR = "Vickie L. Kline" ,TITLE = " Spirit Guides of Cyberspace" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/position/kline.html)" ,ABSTRACT = {Format: HTML Document (5K). Audience: Non-technical. Librarians and futurologists.. References: 0. Links: 1. Relevance: Low. Abstract: A futuristic view of what librarians might be once virtual reality is commonplace. Told as a sci-fi story. } } @INPROCEEDINGS{lwk+94 ,AUTHOR = "Bede Liu and Wayne Wolf and Sanjeev Kulkarni and Andrew Wolfe and Hisashi Kobayashi and Fred Greenstein and Ira Fuchs and Arding Hsu and Farshid Arman and Yiqing Liang" ,TITLE = " The Princeton Video Library of Politics" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/position/wolf.html)" ,ABSTRACT = {Format: HTML Document (8K) . Audience: Digital library funders. References: 0. Links: 1. Relevance: Low. Abstract: Discusses the problems with searching, browsing and indexing video. } } @INPROCEEDINGS{sanc94 ,AUTHOR = "J. Alfredo S\'{a}nchez" ,TITLE = " User Agents in the Interface to Digital Libraries" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/position/sanchez.html)" ,ABSTRACT = {Format: HTML Document (7K) . Audience: Non-technical. References: 3. Links: 1. Relevance: Low-medium. Abstract: Suggests user or interface agents are a valuable organizational tool. "Examples of missions that can be delegated to agents in a digital library include notifying the user when information of interest is added or upd ated, filtering retrieved information according to the user's needs or preferences, and handling routine administrative procedures in the library (such as copyright and billing procedures). Agents may also provide hints to the user bas ed on their knowledge of the library or on observed usage by other users, or contact other users (or user agents) to obtain needed information." Goes on to list properties that agents should have like: security, inspectability, adapti vity, etc. } } @INPROCEEDINGS{sp94 ,AUTHOR = "Gordon K. Springer and Timothy B. Patrick" ,TITLE = " Translating Data to Knowledge in Digital Libraries" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/position/springer.html)" ,ABSTRACT = {Format: HTML Document (8K) . Audience: Non technical, funders. References: 3. Links: 1. Relevance: Low. Abstract: Argues for the need for "filters" programs which will turn the use of the web from document retrieval to information retrieval. A large number of user and task specific filters will be required. } } @INPROCEEDINGS{woel94 ,AUTHOR = "Darrell W. Woelk" ,TITLE = " Carnot Intelligent Agents and Digital Libraries" ,BOOKTITLE = dl94 ,YEAR = "1994" ,LINKS = "(title:www:http://www.csdl.tamu.edu/DL94/position/woelk.html)" ,ABSTRACT = {Format: HTML Document() . Audience: Digital Library researchers. References: 3. Links: 1. Relevance: Medium-Low. Abstract: Suggests the use of agents which are "automatically programmed with the knowledge necessary to map among different data models, query languages, and database schemas." Relies on having a pre-defined "enterprise mod el" (common ontology) and mappings for all the individual databases. } } @INPROCEEDINGS{kahi94 ,AUTHOR = "Brian Kahin" ,TITLE = " The Strategic Environment for Protecting Multimedia" ,BOOKTITLE = " IP Workshop Proceedings" ,YEAR = "1994" ,LINKS = "(title:www:http://www.cni.org/docs/ima.ip-workshop/Kahin.html)" ,ABSTRACT = {Format: HTML Document (23K + pictures). Audience: Non technical, general public. References: 0. Links: 0. Relevance: medium. Abstract: A very good big picture overview that covers a broad range of issues, from desirability of technological protection of IP, to the government's role, to past models of protection. } } @INPROCEEDINGS{linn94 ,AUTHOR = "R.J. (Jerry) Linn" ,TITLE = " Copyright and Information Services in the Context of the National Research and Education Network" ,BOOKTITLE = " IP Workshop Proceedings" ,YEAR = "1994" ,LINKS = "(title:www:http://www.cni.org/docs/ima.ip-workshop/www/Linn.html)" ,ABSTRACT = {Format: HTML Document (34K + pictures). Audience: Computer scientists, politicians. References: 0. Links: 0. Relevance: Medium-Low. Abstract: Argues that the 1991 High Performance Computing act (which stipulates that the "Network" shall ensure copyright laws are obeyed) is unenforceable. Suggests that the responsibility for enforcement should be at the app lication level. Outlines a system of software envelopes, digital signatures, time stamps, and special purpose, limited capability viewers to ensure protection. Also proposes an amendment to HPC 1991. } } @INPROCEEDINGS{eber94 ,AUTHOR = "Joseph L. Ebersole" ,TITLE = " Response to Dr. Linn's Paper" ,BOOKTITLE = " IP Workshop Proccedings" ,YEAR = "1994" ,LINKS = "(title:www:http://www.cni.org/docs/ima.ip-workshop/www/Ebersole.html)" ,ABSTRACT = {Format: HTML Document (15K). Audience: Readers of Dr. Linn's article, lawyers. References: 5. Links: 0. Relevance: Low-medium. Abstract: Discusses the differences between a common carrier, distributor, and publisher. Also discusses trade secrets, fair use. } } @INPROCEEDINGS{perr94 ,AUTHOR = "Henry H. Perritt, Jr." ,TITLE = " Permission Headers and Contract Law" ,BOOKTITLE = " IP WOrkshop Proceedings" ,YEAR = "1994" ,LINKS = "(title:www:http://www.cni.org/docs/ima.ip-workshop/Perritt.html)" ,ABSTRACT = {Format: HTML Document (71K). Audience: Public policy, lawyers, and developers. References: 47 notes. Links: 0. Relevance: Medium. Abstract: Focusing primarily on intellectual property, this article covers a lot of ground. Briefly describes the CNRI copyright management project, argues for "permission headers" that describe how each of the various protected rights (viewing, copying, preparing derivative works, etc) can be in the header, along with economic information. Describes whether digitally signed contracts are likely to be legally enforceable (they probably are), and under what ci rcumstances electronic records are court-admissable (when they are generated as a regular course of business, and there's no reason to doubt them). Argues against general encryption, too expensive & inconsistent with the open market o f ideas. Seeks legal protection commensurate with the value of a transaction. } } @INPROCEEDINGS{gs94 ,AUTHOR = "Branko Gerovac and Richard J. Solomon" ,TITLE = " Protect Revenues, Not Bits: Identify Your Intellectual Property" ,BOOKTITLE = " IP Workshop Proceedings" ,YEAR = "1994" ,LINKS = "(title:www:http://www.cni.org/docs/ima.ip- workshop/www/Gerovac.Solomon.html)" ,ABSTRACT = {Format: HTML Document (40K). Audience: Standards committees, general technologists, technical sections. References: 14 footnotes. Links: 0 . Relevance: low-medium. Abstract: Discusses a header-based approach to identifying data streams, focusing on video domains. Gives a brief history of copyrights. Gives desiderata for standards/design to ensure interoperability, flexibility, extensib ility, etc. Gives concrete examples of encoding used for certain applications. } } @INPROCEEDINGS{ur94 ,AUTHOR = "Luella Upthegrove and Tom Roberts" ,TITLE = " Intellectual Property Header Descriptors: A Dynamic Approach" ,BOOKTITLE = " IP Workshop Proceedings" ,YEAR = "1994" ,LINKS = "(title:www:http://www.cni.org/docs/ima.ip- workshop/www/Upthegrove.Roberts.html)" ,ABSTRACT = {Format: HTML Document(). Audience: DL Researchers, librarians. References: 0. Links: 0. Relevance: Low-Medium. Abstract: Very sketchy outline of approach for managing IP by using trusted systems, local repositories contact remote (IP Owner's) repositories. Documents have headers with "global header descriptor contain a set of data ele ments that identify intellectual property: Ownership, Permitted Uses, Royalty Compensation, and IP Attributes." } } @INPROCEEDINGS{sirb94 ,AUTHOR = "Marvin A. Sirbu" ,TITLE = " Internet Billing Service Design and Prototype Implementation" ,BOOKTITLE = " IP Workshop Proceedings" ,YEAR = "1994" ,LINKS = "(title:www:http://www.cni.org/docs/ima.ip-workshop/www/Sirbu.html)" ,ABSTRACT = {Format: HTML Document (33K + 5 pictures). Audience: Service providers and users . References: 4 notes. Links: 0. Relevance: Medium-High. Abstract: Details an account-based billing server. Lists design requirements, and motivates the need for such a service. Describes the steps involved in a transaction. Buyer sends purchase agreement (including price) to sel ler, seller sends an independent copy to billing server. If both match, server checks that buyer has sufficient funds, then tells service to go ahead. Service does work, then sends invoice to buyer via billing server. Billing server reconciles accounts monthly. Other features: access control, hierarchical organization of corporate accounts, price negotiation & spending caps. } } @INPROCEEDINGS{sg94 ,AUTHOR = "Sergiu S. Simmel and Ivan Godard" ,TITLE = " Metering and Licensing of Resources: Kala's General Purpose Approach" ,BOOKTITLE = " IP Workshop Proceedings" ,YEAR = "1994" ,LINKS = "(title:www:http://www.cni.org/docs/ima.ip- workshop/www/Simmel.Godard.html)" ,ABSTRACT = {Format: HTML Document (72K). Audience: information/software users & producers on the network. References: 9. Links: 0. Relevance: medium. Abstract: Describes a revenue collection mechanism for software/data over in a networked environment. Scheme enables either pay-per-use or licensed arrangements. Stresses recursive nature, so that components may be made up o f other components. Primarily non-technical introduction, followed by specification of API and resource acquiring algorithm in pseudo-code. Mentions concerns of people trying to break the system, and discusses a "cookie" algorithm, b ut it didn't seem like a complete answer. } } @INPROCEEDINGS{kahn94 ,AUTHOR = "Robert E. Kahn" ,TITLE = " Deposit, Registration and Recordation in an Electronic Copyright Management System" ,BOOKTITLE = " IP Workshop Proceedings" ,YEAR = "1994" ,LINKS = "(title:www:http://www.cni.org/docs/ima.ip-workshop/www/Kahn.html)" ,ABSTRACT = {Format: HTML Document (25K + picture). Audience: Good technical introduction . References: 0. Links: 0. Relevance: Medium. Abstract: Reasonable intro to the ideas of encryption, digital signatures, notarization, and a possible mechanism for copyright request *for law abiding users* doesn't deal with protection against caching/passing documents. } } @INPROCEEDINGS{ty94 ,AUTHOR = "J.D. Tygar and Bennet Yee" ,TITLE = " Dyad: A System for Using Physically Secure Coprocessors" ,BOOKTITLE = " IP Workshop Proceedings" ,YEAR = "1994" ,LINKS = "(title:www:http://www.cni.org/docs/ima.ip- workshop/www/Tygar.Yee.html)" ,ABSTRACT = {Format: HTML Document (97K). Audience: Computer Scientists, reasonably technical. References: 9 notes, 65 references. Links: 0. Relevance: Medium-Low. Abstract: Discusses the possibility of secure co-processors, so that clear text is never available on a non-secure co-processor. Also applicable for contracts, authentication, audit trails, and digital cash (which wouldn't require access to a central bank server.) Seems a cumbersome hardware solution, but something similar may be necessary in a "total protection" model. Good glossary of cryptography terms and good bibliography. } } @INPROCEEDINGS{grah94 ,AUTHOR = "Peter S. Graham" ,TITLE = " Intellectual Preservation and Electronic Intellectual Property" ,BOOKTITLE = " IP Workshop Proceedings" ,YEAR = "1994" ,LINKS = "(title:www:http://www.cni.org/docs/ima.ip-workshop/www/Graham.html)" ,ABSTRACT = {Format: HTML Document (43K). Audience: Non-technical, librarians. References: 13 notes. Links: 0. Relevance: Low. Abstract: Discussion of ensuring authenticity of documents, essentially just notarization. } } @INPROCEEDINGS{gris94 ,AUTHOR = "Gary N. Griswold" ,TITLE = " A Method for Protecting Copyright on Networks" ,BOOKTITLE = " IP Workshop Proceedings" ,YEAR = "1994" ,LINKS = "(title:www:http://www.cni.org/docs/ima.ip-workshop/www/Griswold.html)" ,ABSTRACT = {Format: HTML Document(29K). Audience: Computer scientists, specific & somewhat technical. References: 10. Links: 0. Relevance: Medium. Abstract: Secure copyrighted documents by transmitting them in an "envelope" which is the only way to view, print, etc. Periodic & per-use reverification with a server, possible chargeback info. PATENTS APPLIED FOR. } } @INPROCEEDINGS{mq94 ,AUTHOR = "Ben\^{o}it Macq and Jean-Jacques Quisquater" ,TITLE = " Digital Images Multiresolution Encryption" ,BOOKTITLE = " IP Workshop Proceedings" ,YEAR = "1994" ,LINKS = "(title:www:http://www.cni.org/docs/ima.ip- workshop/www/Macq.Quisquater.html)" ,ABSTRACT = {Format: HTML Document (11K). Audience: Computer Scientists, very technical. References: 6. Links: 0. Relevance: low. Abstract: A description of good properties of encryption algorithms applied to image data. A proposal for a technical means to achieve some of those desirable properties. } } @INPROCEEDINGS{mt94 ,AUTHOR = "Kineo Matsui and Kiyoshi Tanaka" ,TITLE = " Video-Steganography: How to Secretly Embed a Signature in a Picture" ,BOOKTITLE = " IP Workshop Proceedings" ,YEAR = "1994" ,LINKS = "(title:www:http://www.cni.org/docs/ima.ip- workshop/www/Matsui.Tanaka.html)" ,ABSTRACT = {Format: ARTICLE NOT AVAILABLE. } } @INPROCEEDINGS{jens94 ,AUTHOR = "Michael Jensen" ,TITLE = " Need-Based Intellectual Property Protection and Networked University Press Publishing" ,BOOKTITLE = " IP Workshop Proceedings" ,YEAR = "1994" ,LINKS = "(title:www:http://www.cni.org/docs/ima.ip-workshop/www/Jensen.html)" ,ABSTRACT = {Format: HTML Document (22K). Audience: Publishers, slightly technical.. References: 0. Links: 0. Relevance: Low-medium. Abstract: A publisher's view on why publisher's won't be irrelevant. Also, a description of the type of security that a publisher would expect (ie, let's not worry about making it perfect, just reasonable.) --a header based system, without details of how to ensure the restrictions are obeyed. Gives a specific list of information that he thinks should be in the header. } } @INPROCEEDINGS{mass94 ,AUTHOR = "Barry M. Massarsky" ,TITLE = " The Operating Dynamics Behind ASCAP, BMI and SESAC, The U.S. Performing Rights Societies" ,BOOKTITLE = " IP Workshop Proceedings" ,YEAR = "1994" ,LINKS = "(title:www:http://www.cni.org/docs/ima.ip- workshop/www/Massarsky.html)" ,ABSTRACT = {Format: HTML Document (25K) . Audience: Business, IP people, non-technical. References: 0. Links: 0. Relevance: Low-Medium. Abstract: Discusses the historical convergence to the current mechanism of music royalties, including some statistics about the monitoring procedure of ASCAP. Argues that the licensing model is to be preferred to the transaction model for multimedia. } } @INPROCEEDINGS{phil94 ,AUTHOR = "Kenneth L. Phillips" ,TITLE = " Meta-Information, The Network of the Future and Intellectual Property Protection" ,BOOKTITLE = " IP Workshop Proceedings" ,YEAR = "1994" ,LINKS = "(title:www:http://www.cni.org/docs/ima.ip-workshop/www/Phillips.html)" ,ABSTRACT = {Format: HTML Document (24K). Audience: Non-technical (some jargon), somewhat business-oriented. References: 4. Links: 0. Relevance: Low. Abstract: Tries to apply information theory ideas of half-life. Description of ATM header packet. Discussion of value of marketing info from charge card & 800 calls. (Claims marketers would pay \$3 per name/address for access to 800-lists, \$3-7 if you could add queries about charge cards.) } ,privateComment = "not too rigorous" } @INPROCEEDINGS{cupi94 ,AUTHOR = "Consortium for University Printing and Information Distribution (CUPID)" ,TITLE = " Protocols and Services (Version 1): An Architectural Overview" ,BOOKTITLE = " IP Workshop Proceedings" ,YEAR = "1994" ,LINKS = "(title:www:http://www.cni.org/docs/ima.ip-workshop/www/CUPID.html)" ,ABSTRACT = {Format: HTML Document (52K). Audience: Publishers, layperson, non-technical. References: 0. Links: 0. Relevance: Low. Abstract: Discussion of the CUPID project, basically just-in-time printing, (of textbooks, e.g.) at trusted printshops. No terminal display, hardcopy only. } } @INPROCEEDINGS{nels94 ,AUTHOR = "Theodor Holm Nelson" ,TITLE = " A Publishing and Royalty Model for Networked Documents" ,BOOKTITLE = " IP Workshop Proceedings" ,YEAR = "1994" ,LINKS = "(title:www:http://www.cni.org/docs/ima.ip-workshop/www/Nelson.html)" ,ABSTRACT = {Format: HTML Document (6K). Audience: Auhtors, publishers, users. References: 1. Links: 0. Relevance: Low-medium. Abstract: Describes the ideas behind Xanadu. Works available at a pay- per-byte rate set by publisher. Embedding of documents (called transclusion) results in original author being paid. } } @INPROCEEDINGS{arno94 ,AUTHOR = "Kenneth Arnold" ,TITLE = " The Body in the Virtual Library: Rethinking Scholarly Communication" ,BOOKTITLE = " JEP" ,LINKS = "(title:www:http://www.press.umich.edu/jep/works/arnold.body.html)" ,ABSTRACT = {Format: HTML Document (41K) . Audience: Scholars, publishers (esp. university press), librarians. References: 10. Links: 1. Relevance: Low-Medium. Abstract: Discusess the future of university presses, in pretty grim terms. Suggests that they lack the capital, staff, and quick reaction time to survive in an electronic world. Considers the Mellon report on scholarly comm unication (which suggests universities get copyrights on books their faculty produce) unreasonable. Thinks that relying on commercial network providers (esp. cable, telecom) would be disastrous. Advocates a non-profit distribution ne twork for scholarly publication. } } @INPROCEEDINGS{arno94b ,AUTHOR = "Kenneth Arnold" ,TITLE = " The Electronic Librarian Is a Verb/The Electronic Library Is Not a Sentence" ,BOOKTITLE = " JEP" ,YEAR = "1994" ,LINKS = "(title:www:http://www.press.umich.edu/jep/works/arnold.eleclib.html)" ,ABSTRACT = {Format: HTML Document (49K) . Audience: Librarians, policy makers. References: 10. Links: 1. Relevance: low. Abstract: A vision of the networked library. Sees the real value of librarians as creating "attention structures" which anticipate the way clients search. } } @INPROCEEDINGS{day94 ,AUTHOR = "Colin Day" ,TITLE = " Economics of Electronic Publishing" ,YEAR = "1994" ,BOOKTITLE = " JEP" ,LINKS = "(title:www:http://www.press.umich.edu/jep/works/colin.econ.html)" ,ABSTRACT = {Format: HTML Document (31K) . Audience: Generalist, academic. References: 1. Links: 0. Relevance: low-medium. Abstract: Discusses the 4 services of publisher and library: Gathering, Selecting, Enhancing, and Informing in terms of benefits provided to academics and society. Argues that distribution of ideas is too important to be exclusively at the mercy of the market place, and should (like theater or public TV) be subsidized, but the majority of cost recovery should still be from users. A rgues that the producers and consumers (university presses and faculty) are largely part of the same institution, so there should be gains, but presses have evolved to be largely independent. } } @INPROCEEDINGS{day94b ,AUTHOR = "Colin Day" ,TITLE = " Pricing Electronic Products" ,BOOKTITLE = " JEP" ,YEAR = "1994" ,LINKS = "(title:www:http://www.press.umich.edu/jep/works/colin.eprice.html)" ,ABSTRACT = {Format: HTML Document (21K) . Audience: publishers, librarians. References: 0. Links: 0 . Relevance: low-medium . Abstract: Economic discussion of publishing. Looks at "first copy" and "incremental copy" costs. Considers ways that publishers can recover first copy costs while still distributing to all for whom it is economically rational (value is greater than incremental cost.) Possible models: 1) "country club", where one pays high up-front dues, but then low per-transaction cost; 2) "differentiated costs" where different products are provided, one at a higher cost with certain features, a second at lower (marginal) cost, e.g., more expensive hardcover comes out first, followed by cheap paperback months later. Mentions 3 specific examples: Project Muse, Chicago Journal of Theoretical Computer Science, and Mathematical Reviews. } } @INPROCEEDINGS{fill94 ,AUTHOR = "Laura Fillmore" ,TITLE = " How We Must Think" ,BOOKTITLE = " JEP" ,LINKS = "(title:www:http://www.obs-us.com/obs/english/papers/think.htm)" ,ABSTRACT = {Format: HTML Version (25K)> . Audience: Publishers. References: 0. Links: 0. Relevance: Low-Medium. Abstract: The president of the Online Bookstore gives her suggestions for other publishers to succeed in the digital age. Think creatively about things that were not possible in paper. Add value by licensing content then giv ing people a framework through which to think about it. Quote from Gregory Rawlins, a computer science professor at Indiana University: "If you're not part of the steamroller, you're part of the road." } } @INPROCEEDINGS{fill94b ,AUTHOR = "Laura Fillmore" ,TITLE = " Internet Publishing in a Borderless Environment: Bookworms into Butterflies" ,BOOKTITLE = " JEP" ,YEAR = "1994" ,LINKS = "(title:www:http://www.obs-us.com/obs/english/papers/butter.htm)" ,ABSTRACT = {Format: HTML Document (18K) . Audience: Publishers. References: 0. Links: 0. Relevance: Low. Abstract: Electronic publishing will need to account for the distributed nature of the Internet. Roles for a publisher include: Imprimatur of quality, content filter. Verifying authenticity of the files. Creating context ar ound core content; Developing and maintaining an equitable royalty system based on number of accesses. Customizing the content for the readers. } } @INPROCEEDINGS{fill94c ,AUTHOR = "Laura Fillmore" ,TITLE = " Online Publishing: Threat or Menace?" ,BOOKTITLE = "JEP" ,YEAR = "1994" ,LINKS = "(title:www:http://www.obs-us.com/obs/english/papers/threat.htm)" ,ABSTRACT = {Format: HTML Document (30K) . Audience: General public, publishers. References: 0. Links: 0. Relevance: low. Abstract: One person's view on the future of publishing and books. Time to press has decreased; "non-linear" thinking is encouraged; people use on-line resources differently than traditional books; piracy is not likely to be a big problem; publishers still needed to publicize. } } @INPROCEEDINGS{fish94 ,AUTHOR = "Janet Fisher" ,TITLE = " Copyright: The Glue of the System" ,BOOKTITLE = " JEP" ,YEAR = "1994" ,LINKS = "(title:www:http://www.press.umich.edu/jep/works/fisher.copyright.html)" ,ABSTRACT = {Format: HTML Document (15K) . Audience: Publishers, scholars, authors. References: 0. Links: 0. Relevance: low. Abstract: An MIT Press director gives her position on copyrights: Journal publishers are essential because they 1) take care of requests for reprints, etc and 2) provide the filter which full-text on-line services need to determine quality. Individual authors or their institutions could not do these economically. Does suggest some changes to current law, like allowing authors to copy for their own classes without fee. } } @INPROCEEDINGS{free94 ,AUTHOR = "Lisa Freeman" ,TITLE = " Testimony prepared on behalf of the Association of American University Presses for the National Information Infrastructure Task Force Working Group on Intellectual Property" ,BOOKTITLE = " JEP" ,YEAR = "1994" ,LINKS = "(title:www:http://www.press.umich.edu/jep/works/freeman.nii.html)" ,ABSTRACT = {Format: HTML Document (10K) . Audience: Legislators. References: 0. Links: 0. Relevance: low. Abstract: AAUP believes the current copyright law is sufficient for use in the networked world. The copyright provides a valuable service in designating the "final" (peer-reviewed) copy. Reprint fees, contracts, and copy prot ection should not be mandated but handled by the copyright holders. } } @INPROCEEDINGS{gher94 ,AUTHOR = "Paul Gherman" ,TITLE = " IMAGE VISION: Forging A National Image Alliance" ,BOOKTITLE = " JEP" ,YEAR = "1994" ,LINKS = "(title:www:http://www.press.umich.edu/jep/works/gherman.image.html)" ,ABSTRACT = {Format: HTML Document (11K) . Audience: Image catalogers & users, politicians. References: 0. Links: 0. Relevance: low. Abstract: Argues that all of the search & retrieval issues for bibliographic records are worse for images. There are more of them, there's no standard for representation or indexing. Calls for creation of universal image database, a single standard for representation, and a standard license agreement for image owners.} } @INPROCEEDINGS{gree94 ,AUTHOR = "Philip Greenspun" ,TITLE = " We Have Chosen Shame and Will Get War" ,BOOKTITLE = " JEP" ,YEAR = "1994" ,LINKS = "(title:www:http://www-swiss.ai.mit.edu/philg/research/shame-and- war.html)" ,ABSTRACT = {Format: HTML Document (22K) . Audience: Browser developers, content publishers. References: 7. Links: 13. Relevance: low. Abstract: Quote from conclusion "HTML is inadequate. It lacks sufficient structural and formatting tags to even render certain kinds of fiction comprehensible much less aesthetic. HTML needs style sheets or improved formatting capabilities so that document designers can spare 20 million Internet users from adjusting everything themselves. The META tag in HTML level 2 can be exploited to implement a document typing system. We need to develop a hierarchy of do cument types to facilitate implementation of programs that automatically process Web documents. This type system must support multiple inheritance. " } } @INPROCEEDINGS{kahi94b ,AUTHOR = "Brian Kahin" ,TITLE = " Institutional and Policy Issues in the Development of the Digital Library" ,BOOKTITLE = " JEP" ,YEAR = "1994" ,LINKS = "(title:www:http://www.press.umich.edu/jep/works/kahin.dl.html)" ,ABSTRACT = {Format: HTML Document (31K) . Audience: net users, librarians, publishers. References: 1. Links: 0. Relevance: low-medium. Abstract: Argues that publishers and libraries will fill the same niche in the digital library. Both will have to change. Talks about the Chicago Journal of Theoretical CS, and says that MIT press is making the effort to cha nge the perception of the online journal so it is considered as prestigious as a traditional journal. Worries that drained of traditional revenue sources, publishers will charge much higher reprint fees. Also concerned that there may be a patent in the pipeline that the Patent Office will stupidly allow, causing major problems for the field. } } @INPROCEEDINGS{so94 ,AUTHOR = "E. Sloan and A. Okerson" ,TITLE = " Columbia Working Group on Electronic Texts" ,BOOKTITLE = " JEP" ,YEAR = "1994" ,LINKS = "(title:www:http://www.press.umich.edu/jep/works/okerson.columbia.html)" ,ABSTRACT = {Format: HTML Document (20K) . Audience: Academicians, esp. university librarians and presses. References: 0. Links: 0. Relevance: low. Abstract: Report from a meeting of university representatives on the need to make electronic publishing viable (primarily economic and timeliness) and the prerequisites for doing so (getting critical mass of papers in a field, ease of use, tenure considerations). Suggests universities encourage their faculty to publish on own university pre-print servers, and have differing levels of status for discussion, pre-print, accepted, etc. } } @INPROCEEDINGS{stro94 ,AUTHOR = "William S. Strong" ,TITLE = " Copyright in the New World of Electronic Publishing" ,BOOKTITLE = " JEP" ,YEAR = "1994" ,LINKS = "(title:www:http://www.press.umich.edu/jep/works/strong.copyright.html)" ,ABSTRACT = {Format: HTML Document (29K) . Audience: Publishers. References: 0. Links: 0. Relevance: Low. Abstract: A lawyer talks about the future of copyright and electronic publishing. Argues that people will obey laws and not make lots of illicit copies. Publishers should aid that by keeping prices low, educating public on c opyright and fair use, and have simple licensing agreements. } } @INPROCEEDINGS{ca95 ,AUTHOR = " William T. Crocca and William L. Anderson" ,TITLE = " Delivering Technology for Digital Libraries: Experiences as Vendors" ,BOOKTITLE = " DL '95" ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/crocca/crocca.html)" ,ABSTRACT = {Format: HTML Document (39K + picture). . Audience: Computer scientists and librarians References: 10. Links: 1. Relevance: Low. Abstract: Argues that many of the problems in DL development are not technical, but social and political, as the nature of the work is transformed. Describes two Xerox collaborations with academia, one on scanned documents, a second with a web-based system. Lists some assumptions that are sometimes made, and to what extent they are borne out. Special concerns are standards, which ones to support, and ensuring access to acquisitions in old standards. } } @INPROCEEDINGS{ccw95 ,AUTHOR = "W. Bruce Croft and Robert Cook and Dean Wilder" ,TITLE = " Providing Government Information on the Internet: Experiences with THOMAS" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/croft/croft.html)" ,ABSTRACT = {Format: HTML Document(29K) . Audience: Information retrieval specialists. References: 12. Links: 1. Relevance: Low. Abstract: Describes use of THOMAS, the on-line source of congressional information. Based on the INQUERY engine, offers keyword searches with other advanced features (proximity, weighted averaging, synonyms) which are largely ignored by the user population. The tendency is for short (3 word or less) queries about a single topic. Describes domain-dependent performance enhancements with the ranking algorithms to ensure that relevant hits appear near the top of the ranking. } } @INPROCEEDINGS{wcvb95 ,AUTHOR = " Ian H. Witten and Sally Jo Cunningham and Mahendra Vallabh and Timothy C. Bell" ,TITLE = " A New Zealand Digital Library for Computer Science Research" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/witten/witten.html)" ,ABSTRACT = {Format: HTML Document(27K + pictures). Audience: Computer scientists. References: 18. Links: 13. Relevance: Low-medium. Abstract: Describes a CS Tech Report project in New Zealand. The mg system stores a full text index (in about 5% of the space of the original!). Documents stay on home servers, only index is centralized. Ability to automatically extract ASCII text from PostScript etc. Able to limit search to first page (usually author, title, abstract). Issues: scalability, ability to minimize communication traffic, transparent to providers, largely automatic indexing. } } @INPROCEEDINGS{levy95 ,AUTHOR = "David M. Levy" ,TITLE = " Cataloging in the Digital Order" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/levy/levy.html)" ,ABSTRACT = {Format: HTML Document (34K) . Audience: Net culturists, computer scientists, librarians. References: 25. Links: 1. Relevance: Low. Abstract: Describes the role of catalogers in the traditional library and their prospects in the future. Argues that catalogers impose an order, and their job requires skills that will not be mechanizable--software agents can not do what catlogers do. Raises questions about the nature of digital material with respect to permanence, maintenance, etc. And how digital materials fit in with traditional definitions (What's a publisher or edition?) } } @INPROCEEDINGS{af95 ,AUTHOR = "Mark S. Ackerman and Roy T. Fielding" ,TITLE = " Collection Maintenance in the Digital Library" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/ackerman/ackerman.html)" ,ABSTRACT = {Format: HTML Document(39K + pictures) . Audience: Librarians, web masters. References: 27. Links: 2. Relevance: Low. Abstract: Discusses the problem of collection maintenance in the digital domain, and argues that while some traditional practices will carry over, new methods will have to be created, esp. for dynamic and informal resources. S uggests that some maintenance can be done automatically by agents, and gives 2 examples: MOMSpider, which checks to make sure links are still current and Web:Lookout which notifies user when "interesting" changes are made to a watched page. } } @INPROCEEDINGS{grah95 ,AUTHOR = "Peter S. Graham" ,TITLE = " The Digital Research Library: Tasks and Commitments" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/graham/graham.html)" ,ABSTRACT = {Format: HTML Document(36K) . Audience: Librarians. References: 23. Links: 8. Relevance: Low. Abstract: Discusses technical and organizational challenges which must be met to have a real digital research library. SIgnificant one is obtaining the institutional commitments to ensure longevity of the collection and acces s to it. Discusses some of the required tasks (like cataloging, backup , authentication) at a high level. } } @INPROCEEDINGS{bdkr95 ,AUTHOR = "Shirley Browne and Jack Dongarra and Ken Kennedy and Tom Rowan" ,TITLE = " Management of the Nationale HPCC Software Exchange--A Virtual Distributed Digital Library" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/browne/browne.html)" ,ABSTRACT = {Format: HTML Document (35K + pictures) . Audience: Computer scientists, mathematicians, librarians. References: 15. Links: 13. Relevance: Low-Medium. Abstract: Describes the NHSE software repository, with files kept at authors' sites, but a central index in a common form (prepared manually now, but hopefully automatically later). Includes a special process for submission a nd revision via web forms, with digital signatures (PGP) required for authentication. Accepted files are fingerprinted using MD5 so that modifications can be detected. A scheme of LIFNs (Location Independent FileNames) is essentially a precursor to URN's. } } @INPROCEEDINGS{mckn95 ,AUTHOR = "Cliff McKnight" ,TITLE = " Digital Library Research at Loughborough: The Last Fifteen Years" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/mcknight/mcknight.html)" ,ABSTRACT = {Format: HTML Document(27K) . Audience: Librarians, Journal readers, authors, and publishers. References: 26. Links: 2. Relevance: Low. Abstract: Describes several projects (BLEND, EVELYN, QUARTET, ADONIS, TEJ) taking place in the UK, going back to 1981. Results were rather pessimistic, with computing resources (esp. screen technology) typically not being suff icient to support what was really necessary. On-line publication was no faster than paper publication (referee reports still took as long) and there was the question of whether on-line publication counts toward tenure. One benefit wa s the immediacy with which on-line discussion of articles occured. } } @INPROCEEDINGS{vanh95 ,AUTHOR = "Nancy A. Van House" ,TITLE = " User Needs Assessment and Evaluation for the UC Berkeley Electronic Environmental Library Project" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/vanhouse/vanhouse.html)" ,ABSTRACT = {Format: HTML Document(28K) . Audience: HCI people, librarians. References: 16. Links: 3. Relevance: Low-Medium. Abstract: Starts off with a description of Berkeley's NSF/ARPA/NASA project, focusing on environmental data, particularly water planning for California. Diverse data types, bitmapped pages with OCR text. Describes the proper ties of the task, and the users of the system. Talks about methods of assessing users needs, like interviews, observation, focus groups, etc. Claims that most users' expectations are too low, so user input doesn't provide appropriate goals. } } @INPROCEEDINGS{jc95 ,AUTHOR = "Eric H. Johnson and Pauline A. Cochrane" ,TITLE = " A Hypertextual Interface for a Searcher's Thesaurus" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/johncoch/johncoch.html)" ,ABSTRACT = {Format: HTML Document(34K + pictures) . Audience: Searchers, HCI people. References: 10. Links: 2. Relevance: Low. Abstract: Describes a MS Windows interface for searching using a thesaurus of related terms. Has 3 parts: a hierarchical organization of the terms, a "cloud" of related terms, and a keyword-in-context that tries to match what you type incrementally. The cloud and hierarchy are point and click, and the hierarchy can be expanded and collapsed ala MS Word outline mode. Also capable of handling multi-hierarchies, where a term has multiple roots. } } @INPROCEEDINGS{dh95 ,AUTHOR = "Hugh Davis and Jessie Hey" ,TITLE = " Automatic Extraction of Hypermedia Bundles from the Digital Library" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/davis/davis.html)" ,ABSTRACT = {Format: HTML Document(34K + pictures) . Audience: Digitial library developers and users. References: 21. Links: 1. Relevance: Low. Abstract: Rather than just retrieving a list of "hits" for a query, the system can bundle them, generating hyperlinks on keywords, offer interactive query expansion or contraction. Suggests the addition of a "length" (in minu tes to comprehend) and a "reader level" field of meta-information. } } @INPROCEEDINGS{kjsk95 ,AUTHOR = "Charles Kacmar and Dean Jue and David Stage and Christie Koontz " ,TITLE = " Automatic Creation and Maintenance of an Organizational Spatial Metadata and Document Digital Library" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/kacmar/kacmar.html)" ,ABSTRACT = {Format: HTML Document(37K + pictures). Audience: Librarians, computer scientists, slight govt/business slant. References: 1. Links: 25. Relevance: Low. Abstract: Discusses a geographic information system for environmental data about Florida. Information is organized around "information zones" which are geographic territories. Prototype system in use. } } @INPROCEEDINGS{nf95 ,AUTHOR = "Douglas D. Nebert and James Fullton" ,TITLE = " Use of the ISite Z39.50 Software to Search and Retrieve Spatially- referenced Data" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/nebert/nebert.html)" ,ABSTRACT = {Format: HTML Document(38K + pictures). Audience: Technical, Geographic Information Systems. References: 7. Links: 11. Relevance: Low. Abstract: Discusses the problems of geographic data (tough to index using text keywords), and an approach based on using fields of a Z39.50 database corresponding to bounding rectangle coordinates. By simple comparisons, a document can be judged to be contained within, overlapping, or disjoint with a target area. Describes a prototype, and debates the merits of a server or client based approach to supporting geographic data. } } @MANUAL{ansi95 ,TITLE = "Information Retrieval: Application Service Definition and Protocol Specification" ,organization = "ANSI/NISO" ,note = "Available at http://lcweb.loc.gov/z3950/agency/document.html" ,month = "April" ,year = "1995" ,links = "(title:www:http://lcweb.loc.gov/z3950/agency/document.html)" ,entered-by = "Andreas Paepcke" ,status = "read" ,keywords = "z39.50" ,abstract = {~} } @INPROCEEDINGS{sgz+95 ,AUTHOR = "Shigeo Sugimoto and Seiki Gotou and Yanchun Zhao and Tetsuo Sakaguchi and Koichi Tabata" ,TITLE = " Enhancing Usability of Network-based Library Information System--- Experimental Studies on User Interface for OPAC and of a Collaboration Tool for Library Services" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/sugimoto/sugimoto.html)" ,ABSTRACT = {Format: HTML Document (27K + pictures) . Audience: HCI people, computer scientists. References: 11. Links: 6. Relevance: Low. Abstract: Describes two systems: one, an on-line catalog that uses a bookshelf metaphor (actually displaying spines of books with their titles, height and width from bibliographic data) with ordering by Dewey decimal system. The second system is a collaborative one, between librarian and user Includes video linkage (at 2 frames/sec) and half-duplex audio. Also, a shared workspace where either person can control cursor, button clicks. Runs over Ethernet at 10Mbps. } } @INPROCEEDINGS{djs+95 ,AUTHOR = "Prasun Dewan and Kevin Jeffay and John Smith and David Stotts and William Oliver" ,TITLE = " Early Prototypes of the Repository for Patterned Injury Data" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/dewan/dewan.html)" ,ABSTRACT = {Format: HTML Document (34K + pictures) . Audience: Medical forensics, computer scientists. References: 15. Links: 1. Relevance: Low-Medium. Abstract: Describes a system for collaboration among coroners. Focuses on issues of access rights--people in different roles (lead examiner, toxicologist, judge) see different views of the same data (some fields are read- prote cted). Initial prototype was under the ABC system of UNC, but new prototypes will be web-based. Also hope to incorporate tele-conferencing capabilities. } } @INPROCEEDINGS{spin95 ,AUTHOR = "Amanda Spink" ,TITLE = " Digital Libraries and Sustainable Development? In DL '95 Proceedings" ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/spink/spink.html)" ,ABSTRACT = {Format: HTML Document (25K) . Audience: Social scientists. References: 50. Links: 1. Relevance: None. Abstract: Quote from paper: "Second, we need to consider whether we are encouraging and participating in the development of an unsustainable vision of a global information infrastructure and possibly contributing to a future crisis of human survival? Is the current imperative is toward global industrialization, the development of national and global information infrastructures, the "information society", digital libraries, and the technological development of LDCs sustainable? We need to consider the possible role of digital libraries within alternate futures for humanity? ... We need to understanding the informational dimensions, impacts and implications of sustainable development for digital libraries research. What are the implications for digital libraries if social change and movements diverge away from modernity? What is the relationship between digital libraries and the sustained development of global industrialization? Will our contribution to the solution of global problems through digital libraries evolve or disappear - if the neoclassical view proves unsustainable? What could be the role of digital libraries in down scaling industrial economies to a sustainable society within a basic needs approach?" } } @INPROCEEDINGS{lamb95 ,AUTHOR = "Roberta Lamb" ,TITLE = " Using Online Information Resources: Reaching for the *.*'s" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/lamb/lamb.html)" ,ABSTRACT = {Format: HTML Document (54K) . Audience: Social scientists, HCI people, slight business slant. References: 39. Links: 1. Relevance: Low-medium. Abstract: A literature review of usage of on-line information resources, filling in blocks in the matrix where one axis is research outlook (includes rational, human relations, institutional, and postmodern) and the other axis is usability factors (includes HCI usability, content usability, organizational usability, interorganizational usability). Some of the reviewed studies involve situated users with tasks. Shows that online information is used much les s than predicted. . } } @INPROCEEDINGS{nfl+95 ,AUTHOR = " Peter J. Nuernberg and Richard Furuta and John J. Leggett and Catherine C. Marshall and Frank M. Shipman III" ,TITLE = " Digital Libraries: Issues and Architectures" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/nuernberg/nuernberg.html)" ,ABSTRACT = {Format: HTML Document (33K + pictures) . Audience: Computer scientists, somewhat technical. References: 13. Links: 1. Relevance: Low-medium. Abstract: Argues that digital libraries is an intersection of a number of different fields, with a distinct research agenda from any of them. Divides areas of study into Objects, Meta-objects, and processes, 3 categories whic h may exist for translations of traditional library things to digital library things, or for exclusively new digital library things. Describes a client/server architecture, and shows how it is instantiated for the problem of personali zing information display in a web-based environment. } } @INPROCEEDINGS{sgm95 ,AUTHOR = "Narayanan Shivakumar and H\'ector Garc\'{\i}a-Molina" ,TITLE = " SCAM: A Copy Detection Mechanism for Digital Documents" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/shivakumar.ps)" ,ABSTRACT = {Format: PostScript Version () . Audience: Computer scientists, information retrieval experts, technical. References: 26. Links: 0. Relevance: High. Abstract: Describes SCAM, a word-based registration mechanism for copy detection. Considers traditional IR similarity measures (cosine, vector) and shows how they're lacking for copy detection. Introduces a new measure, and contrasts to sentence-based COPS approach. Experimental results on comparison of Netnews articles. } } @INPROCEEDINGS{ms95 ,AUTHOR = "Kazunori Muraki and Kenji Satoh" ,TITLE = " Penstation: Easy Access to Relevant Facts without Retrieving" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/muraki.ps)" ,ABSTRACT = {Format: PostScript Document (). Audience: Digital library researchers, esp. HCI & natural language. References: 16. Links: 0. Relevance: Low-medium. Abstract: Describes a work-group based document editing facility which provides for "episodic indexing", allowing search & retrieval based on editing events (such as previous cutting & pasting, searching, etc). Also notifies author when someone from the workgroup cites his work. Finally, there is a feature which does predictive searching. As you type, it does approximate parsing (in Japanese) and searches for information related to what you're typing. } } @INPROCEEDINGS{ah95 ,AUTHOR = "Eytan Adar and Jeremy Hylton" ,TITLE = " On-the-fly Hyperlink Creation for Page Images" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/adar/adar.html)" ,ABSTRACT = {Format: HTML Document () . Audience: Digital library researchers. References: 9. Links: 0. Relevance: Low. Abstract: Store pages as bitmaps, and retrieve a cite when user clicks on it, by doing OCR, then passing relevant line to library catalog, as 12 queries of 3 words each (randomly selected from the line) and returning the best scoring results. Somewhat robust to typos in cites, but not too slow. } } @INPROCEEDINGS{pa95 ,AUTHOR = "Robert Pettengill and Guillermo Arango" ,TITLE = " Four Lessons Learned from Managing World Wide Web Digital Libraries" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/pettengill/pettengill.html)" ,ABSTRACT = {Format: HTML Document (23K + pictures). Audience: Web publishers, esp. corporate. References: 12. Links: 1. Relevance: Low-medium. Abstract: Describes the application of software engineering techniques to web maintenance. Keeping separate development and production areas, using automated tools like UNIX's make to process, test and install new documents, and using a versioning control system like VCS to maintain a document history. Suggest a convention in URLs to specify the version number after a comma. } } @INPROCEEDINGS{mw95 ,AUTHOR = "Verne E. McFarland and Steven Wyman" ,TITLE = " Public Access to EPA Superfund Records - A Digital Alternative" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/mcfarland/mcfarland.html)" ,ABSTRACT = {Format: HTML Document (19K). Audience: Government, not too technical, except for system specs. References: 14 . Links: 4. Relevance: Low. Abstract: Describes the benefits of putting government records on CD-ROM. Lower storage costs, greater access, less risk of missing records. } } @INPROCEEDINGS{ps95 ,AUTHOR = "Casey Palowitch and Darin Stewart" ,TITLE = " Automating the Structural Markup Process in the Conversion of Print Documents to Electronic Texts" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/palowitc/palowitc.html)" ,ABSTRACT = {Format: HTML Document(20K) . Audience: Librarians, SGML translators. References: 12. Links: 1. Relevance: Low. Abstract: Describes a project for generating an SGML version of an 1849 medical text. Commercial OCR software that also gives geometric position, font size info is augmented with Perl to infer section boundaries. Yields a 40% reduction in human effort, 8% erroneous tags. } } @INPROCEEDINGS{flyn95 ,AUTHOR = "Kathleen M. Flynn" ,TITLE = " The Knowledge Manager as a Digital Librarian: An Overview of the Knowledge Management Pilot Program at the MITRE Corporation" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/flynn/flynn.html)" ,ABSTRACT = {Format: HTML Document (10K) . Audience: Corporate librarians. References: 0. Links: 1. Relevance: Low. Abstract: Discusses the role of a Knowledge Manager (formerly corporate librarian. In particular, finding and organizing new networked information resources. } } @INPROCEEDINGS{vn95 ,AUTHOR = "Aravindan Veerasamy and Shamkant Navathe" ,TITLE = " Querying, Navigating, and Visualizing a Digital Library Catalog" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/veerasamy/veerasamy.html)" ,ABSTRACT = {Format: HTML Document() . Audience: HCI people. References: 4. Links: 1. Relevance: Low-medium. Abstract: Describes a system similar to TexTiles. A bar graph for each search term (with the retrieved documents along the x-axis) indicating the importance of the term in the document are overlayed. This allows the user to see which documents have which words at a glance. Also handles thesaurus expansion and GUI query generation. Retrieval of related results (other papers from the proceedings or by the author). } } @INPROCEEDINGS{yrs95 ,AUTHOR = "Yuehong Yuan and Stephen Roehrig and Marvin Sirbu" ,TITLE = " Service Models, Operational Decisions and Architecture of Digital Libraries" ,BOOKTITLE = dl95 ,YEAR = "1995" ,LINKS = "(title:www:http://csdl.tamu.edu/DL95/papers/yuan.ps)" ,ABSTRACT = {Format: PostScript Document (). } } @INPROCEEDINGS{gray95 ,AUTHOR = "Robert Gray" ,TITLE = " Content-Based Image Retrieval: Color and Edges" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,ABSTRACT = {Format: Not Yet On-line. Audience: Vision/graphics researchers. References: 15. Links: . Relevance: Low. Abstract: Technical description of implementation of two techniques to retrieve images based on color histograms and edge maps. Implemented and tested on a small (48 image) database. Results mixed at best. Weaknesses identif ied for future work. } } @INPROCEEDINGS{ra95 ,AUTHOR = "Daniela Rus and James Allan" ,TITLE = " Structural Queries in Electronic Corpora" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,ABSTRACT = {Format: Not Yet On-line.. Audience: Information Retrieval, computer scientists. References: 22. Links: . Relevance: Low-Medium. Abstract: Automatic construction of hyperlinks, based on structure of document (inferred from LaTeX source or PostScript image). So, for example, a query relating to a figure would link to definitions, theorems, and proofs re lated to the figure (automatically deduced), possibly over many documents. TexTile like interface, curved into a circle to allow intra-document links. } } @INPROCEEDINGS{sp95 ,AUTHOR = "Klaus Sullow and Rainer Page" ,TITLE = " Hypermedia Browsing and the Online Publishing Process" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,ABSTRACT ={Format: Not Yet Online. Audience: Web users, computer scientists. References: 13. Links: . Relevance: Low-Medium. Abstract: Describes a browser (BWON) with proxy that caches pages locally, but also represents web structure graphically. Graph algorithm adds new nodes leaving old ones in current locations, possible to add filter to determ ine which nodes are added to the graph (filter based on URL. Paper also suggests allowing retrieval of HEAD information separately from full contents.) Can apply different (stronger) filters as you move farther from the focus node, r esulting in a "fish-eye" view. } } @INPROCEEDINGS{bufo95 ,AUTHOR = "John Buford" ,TITLE = " Evaluation of a Query Language for Structured HyperMedia Documents" ,BOOKTITLE = " DAGS '95. " ,YEAR = "1995" ,ABSTRACT = {Format: Not Yet On-line. Audience: Technical. HyTime developers.. References: 17. Links: . Relevance: Low. Abstract: HyTime is an ISO standard for hypermedia time based documents. This paper discusses an implementation of a database and search engine operating in that language. Examples of queries, optimizations, etc. } } @INPROCEEDINGS{elo95 ,AUTHOR = "Sara Elo" ,TITLE = " Augmenting Text: Good News on Disasters" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,LINKS = "(title:www:http://www.cs.dartmouth.edu/~samr/DAGS95/Papers/elo.html)" ,ABSTRACT = {Format: HTML Document (30K + picture) . Audience: General . References: 12. Links: 3. Relevance: Medium. Abstract: News wire stories on disasters are annotated with facts that relate to the reader's local region. (eg, casualties are cast as a multiple of the hometown population). Readers from different locales see different aug mentations. Frames triggered by disaster keywords are filled in with relevant material, which is then "personalized". } } @INPROCEEDINGS{summ95 ,AUTHOR = "Kristen Summers" ,TITLE = " Logical Structure Types for Documents" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,LINKS = "(title:www:http://www.cs.dartmouth.edu/~samr/DAGS95/Papers/summers.html)" ,ABSTRACT = {Format: HTML Document(41K + pictures) . Audience: Computer Scientists, . References: 26. Links: 4. Relevance: Low. Abstract: Attempts to automatically capture the structure of a document from bitmap/PostScript image. Uses geometric distinctions (contours & indentation), marking observables (font type and weight, bullets, rule-lines), linguistic observables (combinations of alphabetic and numeric characters), and contextual observables (presence of other blocks around the target block). } } @INPROCEEDINGS{alle95 ,AUTHOR = "Robert B. Allen" ,TITLE = " Two Digital Library Intefaces which Exploit Hierarchical Structure" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,LINKS = "(title:www:http://www.cs.dartmouth.edu/~samr/DAGS95/Papers/allen.html)" ,ABSTRACT = {Format: HTML Document(33K + pictures) . Audience: General Computer scientists, HCI . References: 22. Links: 1. Relevance: Low-Medium. Abstract: Uses metaphor of hierarchical Dewey Decimal system or faceted (implying a DAG) ACM literature categories to aid UI. Shows graphically where in the hierarchy hits were found for a search.} } @INPROCEEDINGS{will95 ,AUTHOR = "Joseph Willihnganz" ,TITLE = " Debating Mass Communication During the Rise and Fall of Broadcasting" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,ABSTRACT = {Format: Not Yet On-line. } } @INPROCEEDINGS{lisl95 ,AUTHOR = "Curtis Lisle" ,TITLE = " Modeling for Interaction in Virtual Worlds" ,BOOKTITLE = " DAGS '95. " ,YEAR = "1995" ,ABSTRACT = {Format: Not Yet On-line. Audience: computer scinetists, VR, DB, semi-technical. References: 13. Links: . Relevance: Low. Abstract: Argues that VR representations should no longer depend on data structures for efficient rendering, but structures that support efficient interactions with the virtual world. Namely, use an object oriented database. Having multiple participants in a VR experience is crucial, even if they're interacting at different pieces of the environment. } } @INPROCEEDINGS{will95b ,AUTHOR = "Matthew Williams" ,TITLE = " Direct Metaphor and User Interaction in the Electronic Libraries of the Future" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,ABSTRACT = {Format: Not Yet On-line. Audience: General population, HCI people. References: 10. Relevance: High. Abstract: Focuses on a user's interaction with a digital library, arguing for a direct metaphor (books, tables & bookshelves, highlighters, note cards, post-its). Also states importance of information having multiple forms-- wh at appears as a magazine in one context might be note cards in another. Suggests having a "time-based memory of user interaction with the printed word" so that every time you reference something, a trail of your current research threa d is appended. Allows you to search for things like "the magazine article on whales I read last week." } } @INPROCEEDINGS{parb95 ,AUTHOR = "Ian Parberry" ,TITLE = " The Internet and the Aspiring Games Programer" ,BOOKTITLE = " DAGS '95" ,YEAR = 1995 ,ABSTRACT = {Format: Not Yet On-line. Audience: College instructors. References: 12. Abstract: Describes a game-programming course offered at U. of North Texas, and argues that it's a legitimate means to teach students a lot about computer science while providing them with a practical skill. Describes differe nt distribution models (shareware, freeware, nagware, etc). } } @INPROCEEDINGS{plan95 ,AUTHOR = "Harry Plantinga" ,TITLE = " Digital Libraries and Large Text Documents on the World Wide Web" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,LINKS = "(title:www:http://www.cs.dartmouth.edu/~samr/DAGS95/Papers/plantinga.html)" ,ABSTRACT = {Format: HTML Document (17K) . Audience: HTML publishers, Webmasters, Browser builders. References: 6 notes. Links: 8. Relevance: Low. Abstract: Considers the problem of reference materials done in HTTP. Most people want to access only a particular section, but the HTTP model requires transferring the whole document. Describes a "Pager" (CGI script) that fin ds the desired section and returns it as its own document. Could preprocess documents and index them, parse to ensure it's valid HTML. Closes with concrete suggestions for UI features to ease reading books over Web. } } @INPROCEEDINGS{gree95b ,AUTHOR = "Adrienne GreenHeart" ,TITLE = " Making Multimedia Work for Women" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,links = "(title:www:http://www.apc.net/adrienne/eppr.html)" ,ABSTRACT = {Format: HTML Document (7K) Audience: Women writers, readers. References: 6. (though not in on-line version) Links: 1. Abstract: Argues that the non-linear nature of multimedia fits better with the more cyclical nature of female life, and the non-linear way that many women authors write. The new medium offers women a chance to fight the patria rchy of tradition. } } @INPROCEEDINGS{pst95 ,AUTHOR = "Georgia Panagopoulou and Spiros Sirmakessis and Athanasios Tsakalidis" ,TITLE = " PH Model: A Persistent Approach to Versioning in Hypertext Systems" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,ABSTRACT = {Format: Not Yet On-line. Audience: Hypertext users and developers. References: 20. Relevance: Medium-High. Abstract: Presents an approach for full persistence in hypertext systems. Not only are old versions kept around, but you can also start modifications from any version. Works by keeping information about each link-- the version number it was associated with, whether it's been updated, access rights, whether it's part of an aggregation. There is also a version tree which shows which versions result from modifications from other versions. Then, based on the version you're starting with and the preorder traversal of the version tree, the system determines which links are "current" for you. Some of the analysis (eg, O(1) worst case per access step) seem suspect (it seems like you need to t raverse the version tree), but interesting ideas. } } @INPROCEEDINGS{mart95 ,AUTHOR = "David Martland" ,TITLE = " Developing and Using Documentation Tools for Setext" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,ABSTRACT = {Format: Not Yet On-line. Audience: Authors. References: 14. Relevance: Low-Medium. Abstract: Describes an alternative markup language called Setext. Simpler than HTML and LaTeX, it relies on special formatting characters like ~ to indicate ~italics~, directives (which allow specifying destinations of links) , and positions of formatting (eg, character in position 1). LaTeX and HTML may be automatically generated from Setext, and plain Setext is more readable than either for plain ASCII. } } @INPROCEEDINGS{rby95 ,AUTHOR = "J. Redi and Y. Bar-Yam" ,TITLE = " InterJournal: A Distributed Refereed Electronic Journal" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,LINKS = "(title:www:http://www.cs.dartmouth.edu/~samr/DAGS95/Papers/redi.html)" ,ABSTRACT = {Format: HTML Document(30K) . Audience: Journal authors, referees, readers, and editors. References: 1. Links: 5. Relevance: Low-medium. Abstract: Describes an implemented system for on-line journal publication. Based on WWW and forms, the system calls for each author to maintain his own articles, while there is a centralized index for searching. Referee proc ess is conducted on-line, and there is an option for public abstract as well. Checksum is generated at submission to ensure the article hasn't been changed. } } @INPROCEEDINGS{ms95b ,AUTHOR = "Hermann Maurer and Klaus Schmaranz" ,TITLE = " J.UCS and Extensions as Paradigm for Electronic Publishing" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,ABSTRACT = {Format: Not Yet On-line. Audience: Journal authors, referees, readers and editors. References: 9. Relevance: Low-medium. Abstract: Describes an implemented system for on-line journal publication. Based primarily on Hyper-G, a web browser with support for access control and a separate link database, rather than having links in the text (thereby allowing links on PostScript). Journal is replicated on servers world-wide. All articles are refereed, may only be changed by adding refereed annotations. Supports both hypertext and PostScript formats. Uses ACM computing reviews k eywords. } } @INPROCEEDINGS{pj95 ,AUTHOR = "Ian Parberry and David S. Johnson" ,TITLE = " The SIGACT Theoretical Computer Science Genealogy: Preliminary Report" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,ABSTRACT = {Format: Not Yet On-line. Audience: Computer Science Theoreticians, trivia buffs. References: 6. Abstract: A web-based application which shows the advisor-student relations among the theoretical CS community. Also allows indexing by letter, university, and country. } } @INPROCEEDINGS{bond95 ,AUTHOR = "Leslie Bondaryk" ,TITLE = " Calculus Modules OnLine: An Internet Multimedia Application" ,BOOKTITLE = "DAGS'95" ,YEAR = "1995" ,LINKS = "(title:www:http://www.cs.dartmouth.edu/~samr/DAGS95/Papers/bondaryk.html)" ,ABSTRACT = {Format: HTML Document(21K + pictures) Audience: Calculus Instructors. References: 13. Links: 16. Abstract: Discusses an architecture for a system that aids in the teaching of calculus. } } @INPROCEEDINGS{ssn95 ,AUTHOR = "Stephan M. Spencer and Jean-Yves Sgro and Max L. Nibert" ,TITLE = "Electronic Publishing of Virus Structures in Novel, Multimedia Formats on the World Wide Web" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,LINKS = "(title:www:http://www.cs.dartmouth.edu/~samr/DAGS95/Papers/viruspaper.html)" ,ABSTRACT = {Format: HTML Document (10K + pictures) . Audience: Molecular virologists. References: 13. Links: 7. Abstract: Describes the advantages of using color and animation to display complex molecules like viruses. Talks about system at U. of Wisconsin- Madison. } } @INPROCEEDINGS{nodi95 ,AUTHOR = "Mark H. Nodine" ,TITLE = " Language Learning via the World Wide Web" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,LINKS = "(title:www:http://www.cs.dartmouth.edu/~samr/DAGS95/Papers/nodine.html)" ,ABSTRACT = {Format: HTML Document (29K + pictures). Audience: People interested in learning Welsh, serving a multimedia course. References: 8. Links: 9. Abstract: Describes a web-based self-paced Welsh language course. Lessons written in setext, mailed in ASCII or converted to HTML. Conversion process automated to add index, etc using Perl scripts. } } @INPROCEEDINGS{gmw95 ,AUTHOR = "Oliver Gunther and Rudolf Muller and Andreas S. Wiegand" ,TITLE = " The Design of MMM: A Model ManageMent System for Time Series Analysis" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,LINKS = "(title:www:http://www.cs.dartmouth.edu/~samr/DAGS95/Papers/mmm.html)" ,ABSTRACT = {Format: HTML Document(46K + pictures) . Audience: Mathematicians, economists, statisticians, computer scientists. References: 37. Links: 13. Relevance: Low. Abstract: Proposes a web-based repository for software implementing time series analysis methods. Such a system would facilitate collaboration, verification of results, and would help build an experience base of which models worked well under which circumstances. Briefly describes the architecture, which requires method implementors to specify the methods in terms of Ypsilon (an abstract class system) classes. } } @INPROCEEDINGS{gp95 ,AUTHOR = "Chetan Gopal and Roger Price" ,TITLE = " Multimedia Information Delivery and the MHEG Standard" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,ABSTRACT = {Format: Not Yet On-line. Audience: Multimedia standards setters, developers - technical. References: 11. Relevance: Low. Abstract: Describes the MHEG standard being developed for multimedia objects and applications. Designed to deliver real-time interchange of multimedia objects over wide area networks.} } @INPROCEEDINGS{seco95 ,AUTHOR = "Glen M. Secor" ,TITLE = " Legal Aspects of Electronic Publishing: Look Both Ways Before Crossing This Street" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,ABSTRACT = {Format: Not Yet On-line. Audience: Publishers and authors. References: 9. Relevance: Low. Abstract: An attorney's point of view on the problems of electronic rights for published works. Problems include: Moral rights (much easier for a work to be incorporated into something else in a way the author doesn't like); duration of rights and what rights are granted--publishers have typically asked for rights in "all media hereinafter discovered", something authors are wary of giving away, esp. when many publishers aren't really in the position to exp loit electronic rights. How are royalties granted in the electronic age? Should they be higher because costs are lower, or lower because of new costs of transferring work? Should the publisher have the right to sublicense? Bottom l ine: it's a very unclear area. Forethought can help, as well as an understanding of other parties' positions. } } @INPROCEEDINGS{eric95 ,AUTHOR = "John S. Erickson" ,TITLE = " A Copyright Management System for Networked Interactive Multimedia" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,LINKS = "(title:www:http://picard.dartmouth.edu/~oly/DAGS95.html)" ,ABSTRACT = {Format: HTML Document (13K + pictures) . Audience: Multimedia developers, computer scientists. References: 8. Links: 1. Relevance: Medium-Low. Abstract: Describes a rights management system for multimedia objects called LicensIt. Wrapper around object includes information about author, rights required, and digital signature to verify authenticity. Viewing objects i s through special LicensIt viewers or through commercial applications with LicenseIt plug-ins. } } @INPROCEEDINGS{cc95 ,AUTHOR = "Yee-Hsiang Chang and Ellis Chi" ,TITLE = " HTGraph: A New Method for Information Access Over the World Wide Web" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,LINKS = "(title:www:http://www.cs.dartmouth.edu/~samr/DAGS95/Papers/chang.html)" ,ABSTRACT = {Format: HTML Document (27K + pictures). Audience: Web surfers and computer scientists. References: 11. Links: 0. Relevance: Low. Abstract: Describes a browser which prefetches pages, and builds a graph showing the relationships of those pages, allows you to jump down in the hierarchy. User specified cutoff for how many nodes should be expanded. No atte mpt to automatically cluster. Describes naive data structures to implement a breadth first search of the space. } } @INPROCEEDINGS{ns95 ,AUTHOR = "Raja Neogi and Arindam Saha" ,TITLE = " High Performance IDCT-Based Video Decompression Algorithm and Architecture" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,ABSTRACT = { Not Yet On-line. Nor in proceedings. } } @INPROCEEDINGS{cruz95 ,AUTHOR = "Isabel Cruz" ,TITLE = ". Effective Abstractions in Multimedia" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,LINKS = "(title:www:http://www.cs.tufts.edu/~isabel/dagsannounce.ps), (author:www:http://www.cs.tufts.edu/~isabel)" ,ABSTRACT= {Format: PostScript () . } } @INPROCEEDINGS{henn95 ,AUTHOR = "Albert Henning" ,TITLE = "Dynamic Authoring and Retrieval of Textbook Information: Dartext" ,BOOKTITLE = " DAGS '95" ,YEAR = "1995" ,LINKS = "(title:www:http://hypatia.dartmouth.edu/henning/papers/DAGS95/DAGS95.html)" ,ABSTRACT = {Format: HTML Document (34K + pictures) . Audience: Instructors, students, textbook authors and publishers. References: 15. Links: 6. Relevance: Low-medium. Abstract: A very broad but shallow description of the textbook production business. Argues for a distributed author model, but with publishers that still piece together textbooks from the contributions of instructors, students , etc. CD-ROM versions in addition to on-line. Authors paid according to their contribution. Briefly mentions administration, intellectual property issues. Longer example of physics/engineering systems demo. } } @ARTICLE{vbos96 ,AUTHOR = "Nancy A. Van House and Mark H. Butler and Virginia Ogle and Lisa Schiff" ,TITLE = "User-Centered Iterative Design for Digital Libraries: The Cypress Experience" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1996" ,links = "(title:www:http://www.dlib.org/dlib/february96/02vanhouse.html)" ,month = "Feb" ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{urn96 ,AUTHOR = "The URN Implementors" ,TITLE = "Uniform Resource Names: A Progress Report" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1996" ,links = "(title:www:http://www.dlib.org/dlib/february96/02arms.html)" ,month = "Feb" ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{snfy96 ,AUTHOR = "J. Sairamesh and C. Nikolaou and D. Ferguson and Y. Yemini" ,TITLE = "Economic Framework for Pricing and Charging in Digital Libraries" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1996" ,links = "(title:www:http://www.dlib.org/dlib/february96/forth/02sairamesh.html)" ,month = "Feb" ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{conw96 ,AUTHOR = "Paul Conway" ,TITLE = "Yale University Library's Project Open Book: Preliminary Research Findings" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1996" ,links = "(title:www:http://www.dlib.org/dlib/february96/yale/02conway.html)" ,month = "Feb" ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{kj96 ,AUTHOR = "Judson Knott and Paul Jones" ,TITLE = "SunSITE: Serving Your Internet Needs Since 1992" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1996" ,links = "(title:www:http://www.dlib.org/dlib/february96/02knott.html)" ,month = "Feb" ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{tenn96 ,AUTHOR = "Roy Tennant" ,TITLE = "The Berkeley Digital Library SunSITE" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1996" ,links = "(title:www:http://www.dlib.org/dlib/february96/ucb/02tennant.html)" ,month = "Feb" ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{hujs96 ,AUTHOR = "Jonathan T. Hujsak" ,TITLE = "Digital Libraries and Corporate Technology Reuse" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1996" ,links = "(title:www:http://www.dlib.org/dlib/january96/01hujsak.html)" ,month = "Jan" ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{mcgr96 ,AUTHOR = "Robert E. McGrath" ,TITLE = "Caching for Large Scale Systems: Lessons from the WWW" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1996" ,links = "(title:www:http://www.dlib.org/dlib/january96/ncsa/01mcgrath.html)" ,month = "Jan" ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{lago96 ,AUTHOR = "Carl Lagoze" ,TITLE = "A Secure Repository Design for Digital Libraries" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1995" ,links = "(title:www:http://www.dlib.org/dlib/december95/12lagoze.html)" ,month = "Dec" ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{kess96 ,AUTHOR = "Jack Kessler" ,TITLE = "The French Minitel: Is There Digital Life Outside of the US ASCII Internet? A Challenge or Convergence? " ,JOURNAL = "D-Lib Magazine" ,YEAR = "1995" ,links = "(title:www:http://www.dlib.org/dlib/december95/12kessler.html)" ,month = "Dec" ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{ches95 ,AUTHOR = "David Chesnutt" ,TITLE = "The Model Editions Partnership: Historical Editions in the Digital Age" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1995" ,links = "(title:www:http://www.dlib.org/dlib/november95/11chesnutt.html)" ,month = "Nov" ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{crof95 ,AUTHOR = "W. Bruce Croft" ,TITLE = "What Do People Want from Information Retrieval? (The Top 10 Research Issues for Companies that Use and Sell IR Systems)" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1995" ,links = "(title:www:http://www.dlib.org/dlib/november95/11croft.html)" ,month = "Nov" ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{bish95 ,AUTHOR = "Ann Peterson Bishop" ,TITLE = "Working Towards an Understanding of Digital Library Use: A Report on the User Research Efforts of the NSF/ARPA/NASA DLI Projects" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1995" ,links = "(title:www:http://www.dlib.org/dlib/october95/10bishop.html)" ,month = "October" ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{acke95 ,AUTHOR = "Michael J. Ackerman" ,TITLE = "Accessing the Visible Human Project" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1995" ,links = "(title:www:http://www.dlib.org/dlib/october95/10ackerman.html)" ,month = "October" ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(11K). Audience: Medical professionals,. References: 1. Links: 5. Relevance: None. Abstract: Describes the Visible Human Project (1 mm cross sections of two cadavers), how to obtain the images, how large they are, what IP agreements need to be signed.} } @ARTICLE{lyon95 ,AUTHOR = "Patrice A. Lyons" ,TITLE = "Access to Digital Objects: A Communications Law Strategy" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1995" ,links = "(title:www:http://www.dlib.org/dlib/october95/10lyons.html)" ,month = "Oct" ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{hwc95 ,AUTHOR = "Alexander G. Hauptmann and Michael J. Witbrock and Michael G. Christel" ,TITLE = "News-on-Demand: An Application of Informedia Technology" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1995" ,links = "(title:www:http://www.dlib.org/dlib/september95/nod/09hauptmann1.html)" ,month = {Sep} ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{bdgr95 ,AUTHOR = "Shirley Browne and Jack Dongarra and Eric Grosse and Tom Rowan" ,TITLE = "The Netlib Mathematical Software Repository" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1995" ,links = "(title:www:http://www.dlib.org/dlib/september95/netlib/09browne.html)" ,month = {Sep} ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{garr95 ,AUTHOR = "John R. Garrett" ,TITLE = "Task Force on Archiving of Digital Information" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1995" ,links = "(title:www:http://www.dlib.org/dlib/september95/09garrett.html)" ,month = {Sep} ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{davi95 ,AUTHOR = "James R. Davis" ,TITLE = "Creating a Networked Computer Science Technical Report Library" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1995" ,links = "(title:www:http://www.dlib.org/dlib/september95/09davis.html)" ,month = {Sep} ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{manj95 ,AUTHOR = "B.S. Manjunath" ,TITLE = "Image Browsing in the Alexandria Digital Library (ADL) Project" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1995" ,links = "(title:www:http://www.dlib.org/dlib/august95/alexandria/08manjunath.html)" ,month = {Sep} ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{rand95 ,AUTHOR = "Roberta Y. Rand" ,TITLE = "The Global Change Data and Information System-Assisted Search for Knowledge (GC-ASK) Project" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1995" ,links = "(title:www:http://www.dlib.org/dlib/august95/08rand.html)" ,month = "Aug" ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{lb95 ,AUTHOR = "Richard E. Lucier and Peter Brantley" ,TITLE = "The Red Sage Project: An Experimental Digital Journal Library for the Health Sciences, A Descriptive Overview" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1995" ,links = "(title:www:http://www.dlib.org/dlib/august95/lucier/08lucier.html)" ,month = "Aug" ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{weib95 ,AUTHOR = "Stuart Weibel" ,TITLE = "Metadata: the foundations of resource description" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1995" ,links = "(title:www:http://www.dlib.org/dlib/July95/07weibel.html)" ,month = "Jul" ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{birm95 ,AUTHOR = "William P. Birmingham" ,TITLE = "An agent-based architecture for digital libraries" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1995" ,links = "(title:www:http://www.dlib.org/dlib/July95/07birmingham.html)" ,month = Jul ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(). } } @ARTICLE{arms95 ,AUTHOR = "William Y. Arms" ,TITLE = "Key concepts in the architecture of the digital library" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1995" ,links = "(title:www:http://www.dlib.org/dlib/July95/07arms.html)" ,month = "Jul" ,entered-by = "Steven Ketchpel" ,abstract = {Format: HTML Document(18K + pictures). Audience: computer scientists, digital library researchers. References: 1. Links: 3. Relevance: Medium-low. Abstract: Outlines 8 principles that are important to DLs, a combination of social/economic issues (avoid using words like ``copy'' and ``publish'') and technical ones (basically a sales pitch for the Kahn/Wilensky model of handles, maintenance, and access control.)} } @INPROCEEDINGS{wly+95 ,AUTHOR = "W. Wolf and B. Liu and M. Yeung and B. Yeo and D. Markham" ,TITLE = "Video as Scholarly Material in the Digital Library" ,BOOKTITLE = "Advances in Digital Libraries '95" ,YEAR = "1995" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not Yet Online. Links: . References: . Relevance: . Abstract: .} } @INPROCEEDINGS{swb95 ,AUTHOR = "M. A. Shepherd and C.R. Watters and F.J. Burkowski" ,TITLE = "Digital Libraries for Electronic News" ,BOOKTITLE = "Advances in Digital Libraries '95" ,YEAR = "1995" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not Yet Online. } } @INPROCEEDINGS{tpf+95 ,AUTHOR = "J. Thomas and K. Pennock and T. Fiegel and J. Wise and M. Pottier and A. Schur and D. Lantrip and V. Crow" ,TITLE = "The Visual Analysis of Textual Information: Browsing Large Document Sets" ,BOOKTITLE = "Advances in Digital Libraries '95" ,YEAR = "1995" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not Yet Online. } } @INPROCEEDINGS{ds95 ,AUTHOR = "B. C. Dasai and S. Swiercz" ,TITLE = "WebJounal: Visualization of a Web Journey" ,BOOKTITLE = "Advances in Digital Libraries '95" ,YEAR = "1995" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not Yet Online. } } @INPROCEEDINGS{nr95 ,AUTHOR = "A. Nica and E. A. Rundensteiner" ,TITLE = "Uniform Structured Document Handling Using a Constraint-based Object Approach" ,BOOKTITLE = "Advances in Digital Libraries '95" ,YEAR = "1995" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not Yet Online. } } @INPROCEEDINGS{bsdg95 ,AUTHOR = " R. Boisvert and S. Browne and J. Dongarra and E. Grosse" ,TITLE = "Digital Software and Data Repositories for Support of Scientific Computing" ,BOOKTITLE = "Advances in Digital Libraries '95" ,YEAR = "1995" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not Yet Online. } } @INPROCEEDINGS{wkvb95 ,AUTHOR = "S. Wiesener and W. Kowarschick and P. Vogel and R. Bayer" ,TITLE = "Semantic Hypermedia Retrieval in Digital Libraries " ,BOOKTITLE = "Advances in Digital Libraries '95" ,YEAR = "1995" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not Yet Online. } } @INPROCEEDINGS{gln95 ,AUTHOR = "Y. J. Gao and J.J. Lim and A.D. Narasimhalu " ,TITLE = "Fuzzy Multilinkage Thesaurus Builder in Multimedia Information Systems" ,BOOKTITLE = "Advances in Digital Libraries '95" ,YEAR = "1995" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not Yet Online. } } @INPROCEEDINGS{mg95 ,AUTHOR = "A. Myka and U. Guntzer " ,TITLE = "Fuzzy Full-Text Searches in OCR Databases" ,BOOKTITLE = "Advances in Digital Libraries '95" ,YEAR = "1995" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not Yet Online. } } @INPROCEEDINGS{mb95 ,AUTHOR = "S. Milliner and A. Bouguettaya" ,TITLE = "Data Discovery in Large Scale Heterogeneous and Autonomous Databases" ,BOOKTITLE = "Advances in Digital Libraries '95" ,YEAR = "1995" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not Yet Online. } } @INPROCEEDINGS{rhs+95 ,AUTHOR = "M. E. Rorvig and M. W. Hutchison and R. O. Shelton and S. L. Smith and M. E. Yazbeck " ,TITLE = "An Intelligent Agent for the K-12 Educational Community" ,BOOKTITLE = "Advances in Digital Libraries '95" ,YEAR = "1995" ,links = "(title:www:http://flash.jsc.nasa.gov/smf/KnowledgeRobot.html)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not Yet Online. } } @INPROCEEDINGS{alle95b ,AUTHOR = "R. B. Allen" ,TITLE = "Interface Issues for Interactive Multimedia Documents" ,BOOKTITLE = "Advances in Digital Libraries '95" ,YEAR = "1995" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not Yet Online. } } @INPROCEEDINGS{gershon95 ,AUTHOR = "N. Gershon and W. Ruh and J. LeVasseur and J. Winstead and A. Kleiboemer" ,TITLE = "Searching and Discovery of Resources in Digital Libraries" ,BOOKTITLE = "Advances in Digital Libraries '95" ,YEAR = "1995" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not Yet Online. } } @INPROCEEDINGS{cdd+95 ,AUTHOR = "D.Choy and R. Dievendorff and C. Dwork and J. B. Lotspiech and R. T. Morris and L. C. Anderson and A. E. Bell and S. K. Boyer and T. D. Griffin and B. A. Hoenig and J. M. McCrossin and A. M. Miller and N. J. Pass and F. P estoni and D. S. Picciano " ,TITLE = "The Almaden Distributed Digital Library System" ,BOOKTITLE = "Advances in Digital Libraries '95" ,YEAR = "1995" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not Yet Online. } } @INPROCEEDINGS{fab+95 ,AUTHOR = "J. Frew and M. Aurand and B. Buttenfield and L. Carver and P. Chang and R. Ellis and C. Fischer and M. Gardner and M. Goodchild and G. Hajic and M. Larsgaard and K. Park and M. Probert and T. Smith and Q. Zheng" ,TITLE = "The Alexandria Rapid Prototype: Building A Digital Library for Spatial Information" ,BOOKTITLE = "Advances in Digital Libraries '95" ,YEAR = "1995" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not Yet Online. } } @INPROCEEDINGS{zhao95 ,AUTHOR = "D. Zhao" ,TITLE = "The ELINOR Electronic Library" ,BOOKTITLE = "Advances in Digital Libraries '95" ,YEAR = "1995" ,links = "(title:www:http://ford.mk.dmu.ac.uk/)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not Yet Online. } } @INPROCEEDINGS{dkl95 ,AUTHOR = "J. Davis and D. Krafft and C. Lagoze" ,TITLE = "Dienst: Building a Production Technical Report Server" ,BOOKTITLE = "Advances in Digital Libraries '95" ,YEAR = "1995" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not Yet Online. } } @INPROCEEDINGS{ak95 ,AUTHOR = "Jose-Luis Ambite and Craig A. Knoblock" ,TITLE = "Reconciling Distributed Information Sources" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(author:www:http://www.isi.edu/sims/knoblock/homepage.html), (title:www:ftp://venera.isi.edu/sims/sss95/ambite.ps.Z)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{afjm95a ,AUTHOR = "Robert Armstrong and Dayne Freitag and Thorsten Joachims and Tom Mitchell" ,TITLE = "WebWatcher: A Learning Apprentice for the World Wide Web" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/mitchell.ps.Z)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{bdmw95 ,AUTHOR = "William P. Birmingham and Edmund H. Durfee and Tracy Mullen and Michael P. Wellman" ,TITLE = "The Distributed Agent Architecture of the University of Michigan Digital Library (Extended Abstract)" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/wellman.ps.Z), (author:www:http://ai.eecs.umich.edu/people/kdkd/home.html)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{bh95 ,AUTHOR = "Robin Burke and Kristian J. Hammond" ,TITLE = "Combining Databases and Knowledge Bases for Assisted Browsing" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/burke.ps.Z), (author:www:http://cs-www.uchicago.edu/~burke/)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{bf95 ,AUTHOR = "Sasa Buvac and Richard Fikes" ,TITLE = "A Declarative Formalization of Knowledge Translation" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/buvac.ps.Z), (author:www:http://sail.stanford.edu/buvac)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{de95 ,AUTHOR = "Winton H. E. Davies and Pete Edwards" ,TITLE = "Agent-Based Knowledge Discovery" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/davies.ps.Z), (author:www:http://www.csd.abdn.ac.uk/~pedwards/pedwards.html)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{dj95 ,AUTHOR = "Robert Demolombe and Andrew Jones" ,TITLE = "A Common Logical Framework to Retrieve Information and Meta Information" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/demolombe.ps.Z)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{ellm95 ,AUTHOR = "Thomas Ellman" ,TITLE = "Approximation and Abstraction Techniques for Generating Concise Answers to Database Queries" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/ellman.ps.Z)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{fdfp95 ,AUTHOR = "Adam Farquhar and Angela Dappert and Richard Fikes and Wanda Pratt" ,TITLE = "Integrating Information Sources Using Context Logic" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/farquhar.ps.Z), (author:www:http://www-ksl.stanford.edu/people/axf)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{fefp95 ,AUTHOR = "Richard Fikes and Robert Engelmore and Adam Farquhar and Wanda Pratt" ,TITLE = "Network-Based Information Brokers" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/fikes.ps.Z), (author:www:http://www-ksl.stanford.edu/people/bio/fikes.html)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{fone95 ,AUTHOR = "Leonard N. Foner" ,TITLE = "Clustering and Information Sharing in an Ecology of Cooperating Agents" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/foner.ps.Z), (author:www:http://foner.www.media.mit.edu/people/foner)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{gmh+95 ,AUTHOR = "H\'ector Garc\'{\i}a-Molina and Joachim Hammer and Kelly Ireland and Yannis Papakonstantinou and Jeffrey Ullman and Jennifer Widom" ,TITLE = "Integrating and Accessing Heterogeneous Information Sources in {TSIMMIS}" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/hammer.ps.Z)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{hall95 ,AUTHOR = "Robert J. Hall" ,TITLE = "Agents Helping Agents: Issues in Sharing How-to Knowledge" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/hall.ps.Z)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{hbml95 ,AUTHOR = "Kristian Hammond and Robin Burke and Charles Martin and Steven Lytinen" ,TITLE = "FAQ Finder: A Case-Based Approach to Knowledge Navigation" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/hammond.ps.Z)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{kms95 ,AUTHOR = "Henry Kautz and Al Milewski and Bart Selman" ,TITLE = "Agent Amplified Communication" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/kautz.ps.Z)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). Audience: AI researchers, sociologists. References: .12 Links: . Relevance: Low. Abstract: Many information requests cannot be answered via on-line resources, but must be answered by a human expert. Finding the right person is hard, and usually works by contacting a friend or friend of a friend. This system is designed to automatically generate chains of referrals--each user encodes areas of expertise, and lists colleagues who may be questioned. The system records all mail, incoming & outgoing, and uses that to determine area of expertise of communicators, storing an inverted index of the mail. Then when a question comes up, the system automatically selects relevant people, and sends queries. Their agents intercept, and either route to user, send other referrals, or delete. Simulation results show number of steps to answer for random graphs based on accuracy and responsiveness of referrals.} } @INPROCEEDINGS{hs95 ,AUTHOR = "Scott B. Huffman and David Steier" ,TITLE = "Heuristic Joins to Integrate Structured Heterogeneous Data" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/huffman.ps.Z)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{klss95 ,AUTHOR = "Thomas Kirk and Alon Y. Levy and Yehoshua Sagiv and Divesh Srivastava" ,TITLE = "The Information Manifold" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/kirk.ps.Z), (author:www:http://www.research.att.com/orgs/ssr/people/levy/)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{knob95 ,AUTHOR = "Craig A. Knoblock" ,TITLE = "Integrating Planning and Execution for Information Gathering" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/knoblock.ps.Z), (author:www:http://www.isi.edu/sims/knoblock/homepage.html)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{kl95 ,AUTHOR = "Craig A. Knoblock and Alon Y. Levy" ,TITLE = "Exploiting Run-Time Information for Efficient Processing of Queries" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/levy.ps.Z), (author:www:http://www.isi.edu/sims/knoblock/homepage.html)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{krul95 ,AUTHOR = "Bruce Krulwich" ,TITLE = "Learning User Interests Across Heterogeneous Document Databases" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/krulwich.ps.Z)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{kh95 ,AUTHOR = "Daniel Kuokka and Larry Harada" ,TITLE = "Supporting Information Retrieval via Matchmaking" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/kuokka.ps.Z)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{li95 ,AUTHOR = "Wen-Syan Li" ,TITLE = "Knowledge Gathering and Matching in Heterogeneous Databases" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/li.ps.Z), (author:www:http://www.eecs.nwu.edu/~acura/plan.html)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{mlf95 ,AUTHOR = "James Mayfield and Yannis Labrou and Tim Finin" ,TITLE = "Desiderata for Agent Communication Languages" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/mayfield.ps.Z), (author:www:http://www.cs.umbc.edu/~mayfield)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{mbw95 ,AUTHOR = "Filippo Menczer and Richard K. Belew and Wolfram Willuhn" ,TITLE = "Artificial Life Applied to Adaptive Information Agents" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/menczer.ps.Z), (author:www:http://www-cse.ucsd.edu/users/fil/)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @ARTICLE{nard96 ,AUTHOR = "Bonnie A. Nardi and Vicki L. O'Day" ,TITLE = "Intelligent agents: What we learned in the library" ,JOURNAL = "Libri" ,YEAR = "1996" ,volume = "46" ,number = "2" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @INPROCEEDINGS{opld95 ,AUTHOR = "Tim Oates and M.V. Nagendra Prasad and Victor R. Lesser and Keith Decker" ,TITLE = "A Distributed Problem Solving Approach to Cooperative Information Gathering" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/oates.ps.Z)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{ordi95 ,AUTHOR = "Joann J. Ordille" ,TITLE = "Information Gathering and Distribution in Nomenclator" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/ordille.ps.Z), (author:www:ftp://netlib.att.com/netlib/att/cs/home/ordille.html.Z)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{pe95 ,AUTHOR = "Mike Perkowitz and Oren Etzioni" ,TITLE = "Category Translation: Learning to Understand Information on the Internet" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/perkowitz.ps.Z), (author:www:http://www.cs.washington.edu/homes/map)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{stei95 ,AUTHOR = "David Steier" ,TITLE = "Comparable Datasets in Performance Benchmarking" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/steier.ps.Z)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{sv95 ,AUTHOR = "Peter Stone and Manuela Veloso" ,TITLE = "User-Guided Interleaving of Planning and Execution" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/stone.ps.Z), (author:www:http://www.cs.cmu.edu:8001/Web/People/pstone/pstone- home.html)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{sz95 ,AUTHOR = "Katia Sycara and Dajun Zeng" ,TITLE = "Task-based Multi-agent Coordination for Information Gathering" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/zeng.ps.Z)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{tin95 ,AUTHOR = "Hideaki Takeda and Kenji Iino and Toyoaki Nishida" ,TITLE = "Ontology-supported Agent Communication" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/takeda.ps.Z)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{zilb95 ,AUTHOR = "Shlomo Zilberstein" ,TITLE = "An Anytime Computation Approach to Information Gathering" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,links = "(title:www:ftp://venera.isi.edu/sims/sss95/shlomo.ps.Z), (author:www:http://anytime.cs.umass.edu/~shlomo/)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Compressed PostScript(). } } @INPROCEEDINGS{cran96 ,AUTHOR = "Gregory Crane" ,TITLE = "Building a Digital Library: The Perseus Project as a Case Study in the Humanities" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{msw+96 ,AUTHOR = "Rodger J. McNab and Lloyd A. Smith and Ian H. Witten and Clare L. Henderson and Sally Jo Cunningham" ,TITLE = "Towards the Digital Music Library: Tune Retrieval from Acoustic Input" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{lggp96 ,AUTHOR = "Wei Li and Susan Gauch and John Gauch and Kok Meng Pua" ,TITLE = "VISION: A Digital Video Library" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{bdhk96 ,AUTHOR = "Allen Brewer and Wei Ding and Karla Hahn and Anita Komlodi" ,TITLE = "The Role of Intermediary Services in Emerging Digital Libraries" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{ls96 ,AUTHOR = "Gregory H. Leazer and Richard P. Smiraglia" ,TITLE = "Toward the Bibliographic Control of Works: Derivative Bibliographic Relationships in an Online Union Catalog" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{lin96 ,AUTHOR = "Xia Lin" ,TITLE = "Graphical Table of Contents" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{pz96 ,AUTHOR = "Nikos Pediotakis and Mountaz Zizi" ,TITLE = "Visual Relevance Analysis" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{smf+96 ,AUTHOR = "Tetsuo Sakaguchi and Akira Maeda and Takehisa Fujita and Shigeo Sugimoto and Koichi Tabata" ,TITLE = "A Browsing Tool of Multi-lingual Documents for Users without Multi-lingual Fonts" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{bras96 ,AUTHOR = "Jack Brassil" ,TITLE = "SEPTEMBER - Secure Electronic Publishing Trial" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{dhyg96 ,AUTHOR = "Raymond J. D'Amore and Daniel J. Helm and Puck-Fai Yan and Stephen A. Glanowski" ,TITLE = "MITRE Information Discovery System" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{davi96 ,AUTHOR = "James R. Davis" ,TITLE = "Creating a Networked Computer Science Technical Report Library" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{gm96 ,AUTHOR = "Geri Gay and June P. Mead" ,TITLE = "The Common Ground Surrounding Access: Theoretical and Practical Perspectives" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{gior96 ,AUTHOR = "Richard Giordano" ,TITLE = "Digital Libraries and Impacts on Scientific Careers" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{ksc96 ,AUTHOR = "Hyunki Kim and Hakgene Shin and Jaewoo Chang" ,TITLE = "An Object-Oriented Hypermedia System for Structured Documents" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{mp96 ,AUTHOR = "William E. Moen and John Perkins " ,TITLE = "The Cultural Heritage Information Online Project: Demonstrating Access to Distributed Cultural Heritage Museum Information " ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{pc96 ,AUTHOR = "Varna Puvvada and Roy H. Campbell" ,TITLE = "Inverse Mapping in the Handle Management System" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{rcf96 ,AUTHOR = "Roberta Y. Rand and Betty Coyle-Friedman" ,TITLE = "GC-ASK: A Prototype Information Discovery Project for the Global Change Data and Information System" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{reye96 ,AUTHOR = "Joan A. Reyes" ,TITLE = "The Electronic Reserve System at Penn State University" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{rkbh96 ,AUTHOR = "Ruth A. Ross and Lois F. Kelso and Gary R. Broughton and Edward J. Hopkins" ,TITLE = "Providing Multiple Levels of Difficulty in EarthLab's Digital Library" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{syfn96 ,AUTHOR = "J. Sairamesh and Y. Yemini and D. F. Ferguson and C. Nikolaou" ,TITLE = "A Framework for Pricing Services in Digital Libraries" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{scho96 ,AUTHOR = "Werner Schoggl" ,TITLE = "Establishing Computer-Based Information Services in the School Library" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{bess96 ,AUTHOR = "Howard Besser" ,TITLE = "MESL Project Description" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{nsp96 ,AUTHOR = "Chris North and Ben Shneiderman and Catherine Plaisant" ,TITLE = "User Controlled Overviews of an Image Library: A Case Study of the Visible Human" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{ok96 ,AUTHOR = "Jason Orendorf and Charles Kacmar" ,TITLE = "A Spatial Approach to Organizing and Locating Digital Libraries and Their Content" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{lyyb96 ,AUTHOR = "Yong Kyu Lee and Seong-Joon Yoo and Kyoungro Yoon and P. Bruce Berra " ,TITLE = "Index Structures for Structured Documents" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{pw96 ,AUTHOR = "Thomas A. Phelps and Robert Wilensky" ,TITLE = "Toward Active, Extensible, Networked Documents: Multivalent Architecture and Applications" ,BOOKTITLE = dl96 ,YEAR = "1996" ,address = "Bethesda, Maryland" ,pages = "100--108" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{fmsl96 ,AUTHOR = "Richard Furuta and Catherine C. Marshall and Frank M. Shipman III and John J. Leggett" ,TITLE = "Physical Objects in the Digital Library" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{spcm96 ,AUTHOR = "Tomek Strzalkowski and Jose Perez-Carballo and Mihnea Marinescu" ,TITLE = "Natural Language Information Retrieval In Digital Libraries" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{sjcc96 ,AUTHOR = "Bruce R. Schatz and Eric H. Johnson and Pauline A. Cochrane and Hsinchun Chen" ,TITLE = "Interactive Term Suggestion for Users of Digital Libraries: Using Subject Thesauri and Co-occurrence Lists for Information Retrieval" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{murp96 ,AUTHOR = "Lisa D. Murphy" ,TITLE = "Information Product Evaluation as Asynchronous Communication in Context: A Model for Organizational Research" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{ks96 ,AUTHOR = "Robert B. Kellogg and Madhan Subhas" ,TITLE = "Text to Hypertext: Can Clustering Solve the Problem in Digital Libraries?" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{mhrc96 ,AUTHOR = "R. Manmatha and Chengfeng Han and E. M. Riseman and W. B. Croft" ,TITLE = "Indexing Handwriting Using Word Matching" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{sgm96 ,AUTHOR = "Narayanan Shivakumar and H\'ector Garc\'{\i}a-Molina" ,TITLE = "Building a Scalable and Accurate Copy Detection Mechanism" ,BOOKTITLE = dl96 ,YEAR = "1996" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1996-51)" ,entered-by = "Steven Ketchpel" ,abstract = {Format: pdf, ps} } @INPROCEEDINGS{beck96 ,AUTHOR = "Herb Becker" ,TITLE = "The Role of the Library of Congress in the National Digital Library" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{thom96 ,AUTHOR = "Richard E. Thompson" ,TITLE = "Agricultural Network Information Center (AgNIC): A Model for Access to Distributed Resources" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{mccr96 ,AUTHOR = "Alexa T. McCray" ,TITLE = "Knowledge-Based Biomedical Information Retrieval" ,BOOKTITLE = "Proceedings of DL'96" ,YEAR = "1996" ,entered-by = "Steven Ketchpel" ,abstract = {Format: Not yet online. } } @INPROCEEDINGS{sigmodgloss, AUTHOR="Gravano, Luis and Garc\'{\i}a-Molina, H\'ector and Tomasic, Anthony", TITLE="The effectiveness of {{\em GlOSS}} for the text-database discovery problem", YEAR="1994", MONTH= May, BOOKTITLE=sigmod94, ENTERED-BY = "Luis Gravano", LINKS = "(title:www:http://dbpubs.stanford.edu/pub/1994-34)", ABSTRACT = {The popularity of on-line document databases has led to a new problem: finding which text databases (out or many candidate choices) are the most relevant to a user. Identifying the relevant databases for a given query is the text database discovery problem. The first part of this paper presents a practical solution based on estimating the result size of a query and a database. The method is termed GLOSS-Glossary of Servers Server. The second part of this paper evaluates the effectiveness of GLOSS based on a trace of real user queries. In addition, we analyze the storage cost of our approach.} } @ARTICLE{paep96b ,AUTHOR = "Andreas Paepcke" ,TITLE = "Searching is Not Enough: {What} We Learned On-Site" ,JOURNAL = "{D-Lib} Magazine" ,YEAR = "1996" ,MONTH = "May" ,entered-by = "Michelle Baldonado" ,abstract = {~} ,links = "(title:www:http://www.dlib.org/dlib/may96/stanford/05paepcke.html)" } @ARTICLE{paep96c ,AUTHOR = "Andreas Paepcke" ,TITLE = "Information Needs in Technical Work Settings and their Implications for the Design of Computer Tools" ,JOURNAL = "Computer Supported Cooperative Work: The Journal of Collaborative Computing" ,YEAR = "1996" ,volume = "5" ,entered-by = "Michelle Baldonado" ,pages = "63--92" ,abstract = {~} ,links = "(title:www:http://dbpubs.stanford.edu/pub/1996-80)" } @INPROCEEDINGS{cous96b ,AUTHOR = "Steve B. Cousins" ,TITLE = "A task-oriented interface to a digital library" ,BOOKTITLE = "CHI 96 Conference Companion" ,YEAR = "1996" ,entered-by = "Michelle Baldonado" ,pages = "103--104" ,abstract = {~} ,links = "(title:www:http://dbpubs.stanford.edu/pub/1995-60)" } @ARTICLE{bc96 ,AUTHOR = "Michelle Q Wang Baldonado and Steve B. Cousins" ,TITLE = "Addressing heterogeneity in the networked information environment" ,JOURNAL = "New Review of Information Networking" ,VOLUME = "2" ,YEAR = "1996" ,PAGES = "83--102" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1996-82)" ,entered-by = "Michelle Baldonado" ,abstract = {Several ongoing Stanford University Digital Library projects address the issue of heterogeneity in networked information environments. A networked information environment has the following components: users, information repositories, information services, and payment mechanisms. This paper describes three of the heterogeneity-focused Stanford projects-InfoBus, REACH, and DLITE. The InfoBus project is at the protocol level, while the REACH and DLITE projects are both at the conceptual model level. The InfoBus project provides the infrastructure necessary for accessing heterogeneous services and utilizing heterogeneous payment mechanisms. The REACH project sets forth a uniform conceptual model for finding information in networked information repositories. The DLITE project presents a general task-based strategy for building user interfaces to heterogeneous networked information services. } } @Misc{corba, author = {{Object Management Group}}, title = {{The Common Object Request Broker}: Architecture and Specification}, howpublished = {Accessible at {\tt ftp://\-omg.org/\-pub/\-CORBA}}, year = 1993, month = {Dec}, entered-by = "Michelle Baldonado", links = "(title:www:ftp://omg.org/pub/CORBA)" } @TECHREPORT{starts ,AUTHOR = "Luis Gravano and Chen-Chuan K. Chang and H\'ector Garc\'{\i}a-Molina and Andreas Paepcke" ,TITLE = "{STARTS}: {S}tanford protocol proposal for {I}nternet retrieval and search" ,INSTITUTION = "Stanford University" ,YEAR = 1996 ,MONTH = Aug ,NUMBER = "SIDL-WP-1996-0043; 1997-68" ,LINKS = "(title:www:http://dbpubs.stanford.edu/pub/1997-68)" ,NOTE = "Accessible at http://dbpubs.stanford.edu/pub/1997-68" ,ENTERED-BY = "Luis Gravano" } @MISC{USMARC ,title = "{USMARC} Format for Bibliographic Data: Including Guidelines for Content Designation" ,year = "1994" ,INSTITUTION = "Cataloging Distribution Service, Library of Congress" ,address = "Washington, D.C." ,entered-by = "Michelle Baldonado" ,abstract = {DON'T USE ANY MORE. USE USMARC1 instead.} } @MISC{USMARC1 ,title = "USMARC Concise Formats" ,year = "1998" ,howpublished = "Cataloging Distribution Service" ,address = "Library of Congress, Washington D.C." ,note = "Order at http://lcweb.loc.gov/cds/marcdoc.html" ,entered-by = "Andreas Paepcke" ,keywords = "USMARC, metadata, cataloging" ,abstract = {Latest USMARC reference} } @MISC{GILS ,title = "{Government Information Locator Service (GILS)}" ,year = "1998" ,entered-by = "Michelle Baldonado" ,abstract = {~} ,links="(title:www:http://www.gils.net/index.html)" ,note = "Accessible at {\tt http://www.gils.net/index.html}" } @MISC{geo1 ,title = "{Z39.50} Application Profile for the Content Specification for Digital Geospatial Metadata or {GEO}" ,year = "1995" ,month= Oct ,entered-by = "Luis Gravano" ,links="(title:www:ftp://h2o.usgs.gov/wais/docs/AppProfile_GEO1.2.ps)" ,note = "Accessible at {\tt ftp://h2o.usgs.gov/\-wais/\-docs/\-AppProfile\_GEO1.2.ps}" } @ARTICLE{bcgp97 ,AUTHOR = "Michelle Baldonado and Chen-Chuan K. Chang and Luis Gravano and Andreas Paepcke" ,TITLE = "The {S}tanford {D}igital {L}ibrary Metadata Architecture" ,JOURNAL = "International Journal of Digital Libraries" ,YEAR = "1997" ,month = Feb ,volume = "1" ,number = "2" ,note = "See also http://dbpubs.stanford.edu/pub/1997-56" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1997-56)" ,entered-by = "Chen-Chuan K. Chang" ,keywords = "metadata architecture, interoperability, attribute model, attribute model translation, metadata repository, InfoBus, proxy architecture, heterogeneity, digital libraries" ,abstract = {~} } @MISC{mime, AUTHOR="N. Borenstein and N. Freed", TITLE="{MIME (Multipurpose Internet Mail Extensions)} {P}art {O}ne: {M}echanisms for Specifying and Describing the Format of {I}nternet Message Bodies", NOTE="Internet RFC 1521", MONTH= Sep, YEAR=1993, LINKS = "(title:www:ftp://ds.internic.net/rfc/rfc1521.txt)", ENTERED-BY="Luis Gravano" } @MISC{harvest, AUTHOR="Darren R. Hardy and Michael F. Schwartz and Duane Wessels", TITLE="Harvest User's Manual", NOTE="Accessible at {\tt http://harvest.transarc.com/\-afs/\-transarc.com/\-public/\-trg/\-Harvest/\- user-manual}", MONTH= Jan, YEAR=1996, LINKS = "(title:www:http://harvest.transarc.com/afs/transarc.com/public/trg/Harvest/user -manual)", ENTERED-BY="Luis Gravano" } @INPROCEEDINGS{sigmodstarts ,AUTHOR="Luis Gravano and Chen-Chuan K. Chang and H\'ector Garc\'{\i}a-Molina and Andreas Paepcke" ,TITLE="{STARTS}: {S}tanford Proposal for {I}nternet Meta-Searching" ,BOOKTITLE=sigmod97 ,YEAR="1997" ,ENTERED-BY="Luis Gravano" ,links = "(title:www:http://www- db.stanford.edu/pub/gravano/1996/sigmod97.ps)" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1997-57)" } @INPROCEEDINGS{bald97 ,AUTHOR="Michelle Q Wang Baldonado and Terry Winograd" ,TITLE="{SenseMaker}: An Information-Exploration Interface Supporting the Contextual Evolution of a User's Interests" ,BOOKTITLE=chi97 ,pages = {11--18} ,YEAR="1997" ,month = Mar ,publisher = {ACM Press, New York} ,address = "Atlanta, Ga." ,links = "(title:www:http://dbpubs.stanford.edu/pub/1996-85)" } @TECHREPORT{dliop ,AUTHOR = "Scott W. Hassan and Andreas Paepcke" ,TITLE = "{S}tanford {D}igital {L}ibrary {I}nteroperability {P}rotocol" ,INSTITUTION = "Stanford University" ,YEAR = "1997" ,number = "SIDL-WP-1997-0054; 1997-73" ,note = "Accessible at http://dbpubs.stanford.edu/pub/1997-73" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1997-73)" ,entered-by = "Chen-Chuan K. Chang" } @TECHREPORT{bcgp97b ,AUTHOR = "Michelle Baldonado and Chen-Chuan K. Chang and Luis Gravano and Andreas Paepcke" ,TITLE = "Metadata for Digital Libraries: Architecture and Design Rationale" ,INSTITUTION = "Stanford University" ,YEAR = "1997" ,number = "SIDL-WP-1997-0055; 1997-26" ,note = "Accessible at http://dbpubs.stanford.edu/pub/1997-26" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1997-26)" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {In a distributed, heterogeneous, proxy-based digital library, autonomous services and collections are accessed indirectly via proxies. To facilitate metadata compatibility and interoperability in such a digital library, we have designed a metadata architecture that includes four basic component classes: attribute model proxies, attribute model translators, metadata facilities for search proxies, and metadata repositories. Attribute model proxies elevate both attribute sets and the attributes they define to first-class objects. They also allow relationships among attributes to be captured. Attribute model translators map attributes and attribute values from one attribute model to another (where possible). Metadata facilities for search proxies provide structured descriptions both of the collections to which the search proxies provide access and of the search capabilities of the proxies. Finally, metadata repositories accumulate selected metadata from local instances of the other three component classes in order to facilitate global metadata queries and local metadata caching. In this paper, we outline further the roles of these component classes, discuss our design rationale, and analyze related work.} } @INPROCEEDINGS{kn:bhush ,AUTHOR = "B. Bhushan and others" ,TITLE = "Managing Heterogeneous Networks--Integrator-Based Approach" ,BOOKTITLE = "IFIP Transactions C (Communication Systems)" ,YEAR = 1993 ,entered-by = "Frankie James" ,found-in = "Math/CS TK5105.7.A37 1994" ,keywords = "Object-Oriented Methods; Telecommunication Network Management; Telecommunications Computing" ,abstract = {The authors discuss an object oriented approach to network management. Their goal is to briefly explain a real example of an integrated network management (INM) system. One of the major requirements when looking at information transfer between the managed network and the management system is to mask the heterogeneity of the underlying resources. As an example of the unification of heterogeneity networks, a software called the Integrator has been designed and implemented. The Integrator is a mechanism that provides an object oriented interface to the user (human or network management application programs) to offer a homogeneous view of a world (set of heterogeneous domains) through a model (depicting a formal information view). The Integrator uses two agents to communicate with underlying network elements: an SNMP agent accessing TCP/IP parameters for an Ethernet network through a SNMP agent, and an X.25 interface program doing the same for X.25 parameters through proprietary management software. The concepts of the Integrator has been applied in the EC project PEMMON} } @MISC{kn:nodes ,author = "Steven Moyer" ,title = "N.O.D.E.S. Report" ,year = "1996" ,howpublished = "WWW" ,address = "http://www.gen.com/solutions/nodes/index.htm" ,entered-by = "Frankie James" ,found-in = "Web search" ,abstract = {There is an explosion of information QUANTITY without the capacity to identify the QUALITY of that information. NODES is a planned software system which helps you identify the people and information which fit your needs. It does this by keeping records of which pieces of information on the network are valuable to you, based on your judgments, and making correlations with other users. A public domain database of ratings is essential for this concept to work. Projections are made on a daily basis for each user, based on what other users who share the same interests rate as "good" or "excellent." Each projection is able to be rated. Therefore, over time NODES becomes better and better at finding quality information for you. NODES can be directly configured to operate the way you wish. You can also answer any number of questionnaires, interest surveys, and personality tests to build the database which NODES works with. } } @INPROCEEDINGS{kn:bussl ,AUTHOR = "Christoph Bussler and Stefan Jablonski and Thomas Kirsche and Hans Schuster and Hartmut Wedekind" ,TITLE = "Architectural Issues of Distributed Workflow Management Systems" ,BOOKTITLE = "Parallel Computing Technologies. Third International Conference, PACT-95, Proceedings." ,YEAR = "1995" ,editor = "V. Malyshkin" ,publisher = "Springer-Verlag" ,address = "Berlin, Germany" ,entered-by = "Frankie James" ,found-in = "Math/CS QA76.58.I547 1995" ,keywords = "Business Data Processing; Client-Server Systems; Distributed Databases; Object-Oriented Programming; Software Libraries; Software Performance Evaluation; Systems Re-Engineering" ,abstract = {A specific task of distributed and parallel information systems is workflow management. In particular, workflow management systems execute business processes that run on top of distributed and parallel information systems. Parallelism is due to performance requirements and involves data and applications that are spread across a heterogeneous, distributed computing environment. Heterogeneity and distribution of the underlying computing infrastructure should be made transparent in order to alleviate programming and use. We introduce an implementation architecture for workflow management systems that meets these requirements. Scalability (through transparent parallelism) and transparency with respect to distribution and heterogeneity are the major characteristics of this architecture. A generic client/server class library in an object-oriented environment demonstrates the feasibility of the approach.} } @INPROCEEDINGS{kn:huhns ,AUTHOR = "M.N. Huhns and M.P. Singh" ,TITLE = "Automating Workflows for Service Provisioning: Integrating {AI} and Database Technologies" ,BOOKTITLE = "Proceedings of the Tenth Conference on Artificial Intelligence for Applications" ,YEAR = "1994" ,publisher = "IEEE Computer Society Press" ,address = "Los Alamitos, CA" ,entered-by = "Frankie James" ,found-in = "Math/CS Q334.C654" ,keywords = "Artificial Intelligence; Deductive Databases; Distributed Databases; Management Information Systems; Service Industries" ,abstract = {Workflows are the structured activities that take place in information systems in typical business environments. These activities frequently involve several database systems, user interfaces, and application programs. Traditional database systems do not support workflows to any reasonable extent. Usually, human beings must intervene to ensure their proper execution. We have developed an architecture based on AI technology that automatically manages workflows. This architecture executes on top of a distributed computing environment. It has been applied to automating service provisioning workflows; an implementation that operates on one such workflow has been developed. This work advances the Camel Project's goal of developing technologies for integrating heterogeneous database systems. It is notable in its marriage of AI approaches with standard distributed database techniques.} } @INPROCEEDINGS{kn:medin1 ,AUTHOR = "R. Medina-Mora and K.W. Cartron" ,TITLE = "ActionWorkflow in Use: Clark County Department of Business License" ,BOOKTITLE = "Proceedings of the Twelfth International Conference on Data Engineering" ,YEAR = "1996" ,editor = "S.Y.W. Su" ,publisher = "IEEE Computer Society Press" ,address = "Los Alamitos, CA" ,entered-by = "Frankie James" ,found-in = "Math/CS QA76.9.D3 I5582" ,keywords = "Government Data Processing; Office Automation; Optical Storage; Systems Re-Engineering" ,abstract = {We present the basic concepts of ActionWorkflow and a study of a successful implementation in Clark County Department of Business License. The image/workflow system reengineers a labyrinthine licensing system into simplistic processes that are more customer oriented, yield superior productivity, establish a work in progress tracking mechanism, and archive the resulting licensing processes permanently on an unalterable optical storage system.} } @INPROCEEDINGS{kn:medin2 ,AUTHOR = "R. Medina-Mora and Terry Winograd and Rodrigo Flores and Fernando Flores" ,TITLE = "The ActionWorkflow Approach to Workflow Management Technology" ,BOOKTITLE = "CSCW '92" ,YEAR = "1992" ,editor = "J. Turner and R. Kraut" ,publisher = "ACM" ,address = "New York" ,entered-by = "Frankie James" ,found-in = "Math/CS HD66.C563.1992" ,keywords = "Administrative Data Processing; Groupware" ,abstract = {Describes the ActionWorkflow approach to workflow management technology: this is a design methodology and associated computer software for the support of work in organizations. The approach is based on theories of communicative activity as language/action, and has been developed in a series of systems for coordination among users of networked computers. This paper describes the approach, gives an example of its application, and shows the architecture of a workflow management system based on it.} } @BOOK{kn:elmag ,AUTHOR = "Ahmed K. Elmagarmid" ,TITLE = "Database Transaction Models for Advanced Applications" ,PUBLISHER = "Morgan Kaufmann" ,YEAR = "1992" ,address = "San Mateo, CA" ,entered-by = "Frankie James" ,found-in = "Math/CS QA76.9.D3.D3632 1992" ,keywords = "Database management; Distributed Databases" } @ARTICLE{kn:fuchs ,AUTHOR = "M. Fuchs" ,TITLE = "The User Interface as Document: SGML and Distributed Applications" ,JOURNAL = "Computer Standards \& Interfaces" ,YEAR = "1996" ,month = "January" ,volume = "18" ,number = "1" ,pages = "79--92" ,entered-by = "Frankie James" ,found-in = "Engineering Serials" ,keywords = "SGML; User Interfaces; Active Documents; Distributed Systems; Scripting Languages; Information Browsing" ,abstract = {Multi-user distributed applications running on heterogeneous networks must be able to display user interface components on several platforms. In wide-area public networks, such as the Internet, the mix of platforms and participants in an application will occur dynamically; the user interface will need to coexist with environments completely uncontrolled by the designer. We have dealt with this issue by considering user interfaces as a kind of document specifying the application`s requirements and adopting SGML technology to process them locally. This approach provides new flexibility, with implications for the design of network browsers, such as those of the World Wide Web, and leads to an interesting class of active documents.} } @ARTICLE{kn:salmi ,AUTHOR = "Airi Salminen and others" ,TITLE = "From Text to Hypertext by Indexing" ,JOURNAL = "ACM Transactions on Information Systems" ,YEAR = "1995" ,month = "January" ,volume = "13" ,number = "1" ,pages = "69--99" ,entered-by = "Frankie James" ,found-in = "Math/CS Serials" ,keywords = "Constrained grammars; Grammars; Hypertext; Properties; Structured Text; Text Entities; Text Types; Transient Hypergraphs" ,abstract = {A model is presented for converting a collection of documents to hypertext by means of indexing. The documents are assumed to be semistructured, i.e., their text is a hierarchy of parts, and some of the parts consist of natural language. The model is intended as a framework for specifying hypertextual reading capabilities for specific application areas and for developing new automated tools for the conversion of semistructured text to hypertext. In the model, two well-known paradigms---formal grammars and document indexing---are combined. The structure of the source text is defined by a schema that is a constrained context-free grammar. The hierarchic structure of the source may thus be modeled by a parse tree for the grammar. The effect of indexing is described by the grammar transformations. The new grammar, called an indexing schema, is associated with a new parse tree where some text parts are index elements. The indexing schema may hide some parts of the original documents or the structure of some parts. For information retrieval, parts of the indexed text are considered to be nodes of a hypergraph. In the hypergraph-based information access, the navigation capabilities of hypertext systems are combined with the querying capabilities of information retrieval systems.} } @ARTICLE{kn:celen ,AUTHOR = "Augusto Celentano and others" ,TITLE = "Knowledge-Based Document Retrieval in Office Environments: The Kabiria System" ,JOURNAL = "ACM Transactions on Information Systems" ,YEAR = "1995" ,month = "July" ,volume = "13" ,number = "3" ,pages = "237--268" ,entered-by = "Frankie James" ,found-in = "Math/CS Serials" ,keywords = "Browser; Class; Hypertext; Instance; Knowledge Base; Link; Object Orientation; User Interface; Metadata" ,abstract = {In the office environment, the retrieval of documents is performed using the concepts contained in the documents, information about the procedural context where the documents are used, and information about the regulations and laws that discipline the life of documents within a given application domain. To fulfill the requirements of such a sophisticated retrieval, we propose a document retrieval model and system based on the representation of knowledge describing the semantic contents of documents, the way in which the documents are managed by procedures and by people in the office, and the application domain where the office operates. The article describes the knowledge representation issues needed for the document retrieval system and presents a document retrieval model that captures these issues. The effectiveness of the approach is illustrated by describing a system, named {\em Kabiria}, built on top of such model. The article describes the querying and browsing environments, and the architecture of the system.} } @BOOK{kn:white ,AUTHOR = "Thomas E. White and Layna Fischer" ,TITLE = "New Tools for New Times: The Workflow Paradigm" ,PUBLISHER = "Future Strategies, Inc." ,YEAR = "1994" ,address = "Alameda, CA" ,entered-by = "Frankie James" ,keywords = "Workflow; Organizational Change; Organizational Effectiveness; Quality Control; Information Technology; Information Resources Management; Management Information Systems; Office Practice---Automation" } @ARTICLE{kn:singh ,AUTHOR = "M.P. Singh and M.N. Huhns" ,TITLE = "Automating Workflows for Service Order Processing: Integrating AI and Database Technologies" ,JOURNAL = "IEEE Expert" ,YEAR = "1994" ,month = "October" ,volume = "9" ,number = "5" ,pages = "19--23" ,entered-by = "Frankie James" ,found-in = "Math/CS Serials" ,keywords = "Database Management Systems; Distributed Processing; Knowledge Based Systems; User Interfaces" ,abstract = {We have developed an AI-based architecture that automatically manages workflows, and we have implemented a prototype that executes on top of a distributed computing environment to help a telecommunications company better provide a service that requires coordination among many operation support systems and network elements. The activities involve several database systems, user interfaces, and application programs.} } @INPROCEEDINGS{kn:hoppe ,AUTHOR = "H. Ulrich Hoppe and Jian Zhao" ,TITLE = "C-TORI: An Interface for Cooperative Database Retrieval" ,BOOKTITLE = "5th International Conference, DEXA '94, Database and Expert Systems Applications" ,YEAR = "1994" ,editor = "Dimitris Karagiannis" ,publisher = "Springer-Verlag" ,address = "Berlin, Germany" ,entered-by = "Frankie James" ,found-in = "Math/CS QA76.9.D32 D28" ,keywords = "Information Retrieval, Groupware, CSCW, Database Interfaces" ,abstract = {C-TORI (Cooperative TORI), a cooperative version of TORI (Task-Oriented Database Retrieval Interface), is presented in this paper. It extends interactive query formulation and result browsing by supporting cooperation between multiple users. In the cooperative environment, three basic additional operations are provided: copying, merging and coupling for three types of TORI objects (query forms, result forms, and query history windows). Cooperation with query forms allows end users to jointly formulate queries; cooperation with result forms supports users in jointly browsing through results and in sharing retrieved data without re-accessing the database; cooperative use of query histories yields a specific mechanism to share "memory" between users. The implementation is based on the concept of shared UI objects as an application-independent cooperation and communication model.} } @INPROCEEDINGS{kn:abbot ,AUTHOR = "Kenneth R. Abbott and Sunil K. Sarin" ,TITLE = "Experiences with Workflow Management: Issues for the Next Generation" ,BOOKTITLE = "CSCW '94" ,YEAR = "1994" ,editor = "Richard Furuta and Christine Neuwirth" ,publisher = "ACM" ,address = "New York" ,entered-by = "Frankie James" ,found-in = "Math/CS HD66.C563 1994" ,keywords = "Workflow, business process reengineering" ,abstract = {Workflow management is a technology that is considered strategically important by many businesses, and its market growth shows no signs of abating. It is, however, often viewed with skepticism by the research community, conjuring up visions of oppressed workers performing rigidly-defined tasks on an assembly line. Although the potential for abuse no doubt exists, workflow management can instead be used to help individuals manage their work and to provide a clear context for performing that work. A key challenge in the realization of this ideal is the reconciliation of workflow process models and software with the rich variety of activities and behaviors that comprise ``real'' work. Our experiences with the InConcert workflow management system are used as a basis for outlining several issues that will need to be addressed in meeting this challenge. This is intended as an invitation to CSCW researchers to influence this important technology in a constructive manner by drawing on research and experience.} } @INPROCEEDINGS{kn:neuwi ,AUTHOR = "Christine M. Neuwirth and others" ,TITLE = "Computer Support for Distributed Collaborative Writing: Defining Parameters of Interaction" ,BOOKTITLE = "CSCW '94" ,YEAR = "1994" ,editor = "Richard Furuta and Christine Neuwirth" ,publisher = "ACM" ,address = "New York" ,entered-by = "Frankie James" ,found-in = "Math/CS HD66.C563 1994" ,keywords = "Parameters of interaction, synchronous/asynchronous, collaborative writing, computer-supported cooperative work" ,abstract = {This paper reports research to define a set of interaction parameters that collaborative writers will find useful. Our approach is to provide parameters of interaction and to locate the decision of how to set the parameters with the users. What is new is the progress we have made outlining task management parameters, notification, scenarios of use, as well as some implementation architectures.} } @INPROCEEDINGS{kn:praka ,AUTHOR = "Atul Prakash and Hyong Sop Shim" ,TITLE = "DistView: Support for Building Efficient Collaborative Applications Using Replicated Objects" ,BOOKTITLE = "CSCW '94" ,YEAR = "1994" ,editor = "Richard Furuta and Christine Neuwirth" ,publisher = "ACM" ,address = "New York" ,entered-by = "Frankie James" ,found-in = "Math/CS HD66.C563 1994" ,keywords = "Groupware, multi-user interfaces, collaboration technology, shared windows, active objects, distributed objects, replicated objects, concurrency control" ,abstract = {The ability to share synchronized views of interactions with an application is critical to supporting synchronous collaboration. The paper suggests a simple synchronous collaboration paradigm in which the sharing of the views of user/application interactions occurs at the window level within a multi-user, multi-window application. The paradigm is incorporated in a toolkit, DistView, that allows some of the application windows to be shared at a fine-level of granularity, while still allowing other application windows to be private. The toolkit is intended for supporting synchronous collaboration over wide-area networks. To keep bandwidth requirements and interactive response time low in such networks, DistView uses an object-level replication scheme, in which the application and interface objects that need to be shared among users are replicated. We discuss the design of DistView and present our preliminary experience with a prototype version of the system.} } @INPROCEEDINGS{kn:pacul ,AUTHOR = "Fran\c{c}ois Pacull and others" ,TITLE = "Duplex: A Distributed Collaborative Editing Environment in Large Scale" ,BOOKTITLE = "CSCW '94" ,YEAR = "1994" ,editor = "Richard Furuta and Christine Neuwirth" ,publisher = "ACM" ,address = "New York" ,entered-by = "Frankie James" ,found-in = "Math/CS HD66.C563 1994" ,keywords = "Collaborative editing, distributed groupware, large scale networks, concurrency control" ,abstract = {DUPLEX is a distributed collaborative editor for users connected through a large-scale environment such as the Internet. Large-scale implies heterogeneity, unpredictable communication delays and failures, and inefficient implementations of techniques traditionally used for collaborative editing in local area networks. To cope with these unfavorable conditions, DUPLEX proposes a model based on splitting the document into independent parts, maintained individually and replicated by a kernel. Users act on document parts and interact with co-authors using a local environment providing a safe store and recovery mechanisms against failures or divergence with co-authors. Communication is reduced to a minimum, allowing disconnected operation. Atomicity, concurrency, and replica control are confined to a manageable small context.} } @INPROCEEDINGS{kn:green ,AUTHOR = "Saul Greenberg and David Marwood" ,TITLE = "Real Time Groupware as a Distributed System: Concurrency Control and Its Effect on the Interface" ,BOOKTITLE = "CSCW '94" ,YEAR = "1994" ,editor = "Richard Furuta and Christine Neuwirth" ,publisher = "ACM" ,address = "New York" ,entered-by = "Frankie James" ,found-in = "Math/CS HD66.C563 1994" ,keywords = "Real time groupware, computer supported cooperative work, distributed systems, concurrency control algorithms" ,abstract = {This paper exposes the concurrency control problem in groupware when it is implemented as a distributed system. Traditional concurrency control methods cannot be applied directly to groupware because system interactions include people as well as computers. Methods, such as locking, serialization, and their degree of optimism, are shown to have quite different impacts on the interface and how operations are displayed and perceived by group members. The paper considers both human and technical considerations that designers should ponder before choosing a particular concurrency control method. It also reviews the authors` work-in-progress designing and implementing a library of concurrency schemes in GROUPKIT, a groupware toolkit.} } @BOOK{joha84 ,AUTHOR = "Robert Johansen" ,TITLE = "Teleconferencing and beyond : communications in the office of the future" ,PUBLISHER = "McGraw-Hill" ,YEAR = "1984" ,series = "McGraw-Hill data communications book series" ,entered-by = "Andreas Paepcke" ,keywords = "tightly-coupled collaboration, teleconferencing" } @INPROCEEDINGS{bore88 ,AUTHOR = "Nathaniel Borenstein" ,TITLE = "Cooperative Work in the Andrew Message System" ,BOOKTITLE = cscw88 ,YEAR = "1988" ,entered-by = "Andreas Paepcke" ,found-in = "Terry Winograd's office" ,keywords = "email, collaboration through email, Andrew" ,abstract = {Describes collab-related aspects of Andrew.} } @MISC{sear95 ,author = "Searchlight Software, Inc." ,title = "Searchlight Software's 'Project Odessa' Brings BBS-Like Features to the WEB" ,year = "1995" ,howpublished = "http://www.searchlight.com/odessa/odessa.htm" ,entered-by = "Andreas Paepcke" ,keywords = "conferencing and BBBs on the Web" ,abstract = {~} } @INPROCEEDINGS{conk88 ,AUTHOR = "Jeff Conklin and Michael L. Begeman" ,TITLE = "{gIBIS}: A Hypertext Tool for Exploratory Policy Discussion" ,BOOKTITLE = cscw88 ,YEAR = "1988" ,entered-by = "Andreas Paepcke" ,keywords = "graphical IBIS, conference system, collaborative argumentation system" ,abstract = {~} } @INPROCEEDINGS{stre94 ,AUTHOR = "Norbert A. Streitz and {J\"{o}rg} M. Haake and Jeroen Hol" ,TITLE = "{DOLPHIN}: Integrated Meeting Support across Local and Remote Desktop Environments and LiveBoards" ,BOOKTITLE = cscw94 ,YEAR = "1994" ,entered-by = "Andreas Paepcke" ,keywords = "Live meeting support, collaboration and persistence" ,abstract = {~} } @INPROCEEDINGS{ SALTZER92 ,AUTHOR = "Jerome H. Saltzer" ,TITLE = "Technology, Networks, and the Library of the Year 2000" ,BOOKTITLE = "In Future Tendencies in Computer Science, Control, and Applied Mathematics. Proceedings of the International Conference on the Occasion of the 25th Anniversary of INRIA" ,YEAR = "1992" ,pages = "51-67" ,editor = "A. Bensoussan and J.-P. Verjus" ,publisher = "Springer-Verlag" ,address = "New York" ,entered-by = "Arturo Crespo" ,notes="At http://ltt-www.lcs.mit.edu/ltt-www/Papers/inria.html" ,abstract = {An under-appreciated revolution in the technology of on-line storage, display, and communications will, by the year 2000, make it economically possible to place the entire contents of a library on-line, in image form, accessible from computer workstations located anywhere, with a hardware storage cost comparable to one year's operational budget of that library. In this paper we describe a vision in which one can look at any book, journal, paper, thesis, or report in the library without leaving the office, and can follow citations by pointing; the item selected pops up immediately in an adjacent window. To bring this vision to reality, research with special attention to issues of modularity and scale will be needed, on applying the client/server model, on linking data, and on the implications of storage that must persist for decades. } } @BOOK{ GRAY93 ,AUTHOR = "Jim Gray and Andreas Reuter" ,TITLE = "Transaction Processing: concepts and techniques" ,PUBLISHER = "Morgan Kaufmann Publishers, Inc." ,YEAR = "1993" ,entered-by = "Arturo Crespo" ,abstract = { This is a comprehensive book on transaction processing. Chapter 3 introduces the concept of Fault Tolerance. Chapter 4 presents different transaction models. Chapters 5,6 give an overview of the functionality of the TP monitor. Chapters 7,8 describe concurrency control and its implementation. Chapter 9 give an overview of recovery and how to implement logs. Chapter 10,11 defines a transaction manager and how to implement it. Chapter 12 is a compedium of advanced transaction manager topics including heterogeneous commit coordinators, non-blocking commit coordinators, transfer of commit, optimization of 2-phase commit, and disaster recovery. The rest of the book describes in detail the low level implementation of a transaction processing system, and provides a survery of TP systems in the market. } } @ARTICLE{ PATTERSON88 ,AUTHOR = "David Patterson and Garth Gibson and Randy H. Katz" ,TITLE = "A Case for Redundant Arrays of Inexpensive Disks (RAID)" ,JOURNAL = "SIGMOD Record" ,YEAR = "1988" ,month = Sep ,volume = "17" ,number = "3" ,pages = "109-116" ,entered-by = "Arturo Crespo" ,abstract = { This is the paper that introduced RAIDs. The paper proposes arrays of inexpensive disk as a cheaper, faster, and more scalable alternative to single large disk. The problem is that an array of inexpensive disk has less reliability than a single large disk. The authors propose 5 levels of RAIDs to solve that problem. Level 1 uses mirrored disk, level 2 uses hamming code for ECC, level 3 uses only a single check disk per group, level 4 allows independent reads/writes to the disks, level 5 distributes the check information across all disks. } } @INPROCEEDINGS{ SCHLOSS90 ,AUTHOR = "G.A. Schloss and M. Stonebraker" ,TITLE = "Highly redundant management of distributed data" ,BOOKTITLE = "Proceedings of Workshop on the Management of Replicated Data" ,YEAR = "1990" ,month = "November" ,organization = "IEEE" ,publisher = "IEEE Computing Society" ,pages = "91-95" ,entered-by = "Arturo Crespo" ,abstract = { Introduces the idea of RADDs (Redundant Array of Distributed Disks). This paper expands the idea of RAIDs to disk that are connected by a reliable high speed data communication network. Main results on storage space utilization, I/O performance and reliability are outlined. } } @ARTICLE{ GRAY96 ,AUTHOR = "Jim Gray and Pat Helland and Patrick E. O'Neil and Dennis Shasha" ,TITLE = "Dangers of Replication and a Solution" ,JOURNAL = "SIGMOD" ,YEAR = "1996" ,month = "June" ,pages = "173-82" ,entered-by = "Arturo Crespo" ,abstract = { Update anywhere-anytime-anyway transactional replication has unstable behavior as the workload scales up: a ten-fold increase in nodes and traffic gives a thousand fold increase in deadlocks or reconciliations. Master copy replication (primary copy) schemes reduce this problem. A simple analytic model demonstrates these results. A new two-tier replication algorithm is proposed that allows mobile (disconnected) applications to propose tentative update transactions that are later applied to a master copy. Commutative update transactions avoid the instability of other replication schemes } } @ARTICLE{ SON88 ,AUTHOR = "Sang Hyuk Son" ,TITLE = "Replicated Data Management in Distributed Database Systems" ,JOURNAL = "SIGMOD Record" ,YEAR = "1988" ,month = "December" ,volume = "17" ,number = "4" ,pages = "62-9" ,entered-by = "Arturo Crespo" ,abstract = { This paper classifies different synchronization methods. The dimensions explored are: optimistic vs. pesimistic algorithms, syntactic vs. semantic approaches, majority algorithms, weighted voting algorithms, quorum and ADTs, and special copy approaches. The descriptions underly mechanisms and the type of information they use in ordering the operation of the transactions. } } @ARTICLE{ KING91 ,AUTHOR = "Richard P. King and Nagui Halim and Hector Garcia-Molina and Christos A. Polyzois" ,TITLE = "Management of a Remote Backup Copy for Disaster Recovery" ,JOURNAL = "TODS" ,YEAR = "1991" ,volume = "16" ,number = "2" ,pages = "338-68" ,entered-by = "Arturo Crespo" ,abstract = { A remote backup database system tracks the state of a primary system, taking over transaction processing when disaster hits the primary site. The primary and backup sites are physically isolated so that failures at one site are unlikely to propagate to the other. For correctness, the execution schedule at the backup must be equivalent to that at the primary. When the primary and backup sites contain a single processor, it is easy to achieve this property. However, this is harder to do when each site contains multiple processors and sites are connected via multiple communication lines. The authors present an efficient transaction processing mechanism for multiprocessor systems that guarantees this and other important properties. They also present a database initialization algorithm that copies the database to a backup site while transactions are being processed. } } @ARTICLE{ VINGRALEK94 ,AUTHOR = "Radek Vingralek and Yuri Breitbart and Gerhard Weikum" ,TITLE = "Distributed File Organization with Scalable Cost/Performance" ,JOURNAL = sigmod94 ,YEAR = "1994" ,month = "June" ,pages = "253-64" ,entered-by = "Arturo Crespo" ,abstract = { This paper is perhaps too OS oriented. Nevertheless is a great paper. The paper presents a distributed file organization for record-structured, disk-resident files with key-based exact-match access. The file is organized into buckets that are spread across multiple servers, where a server may hold multiple buckets. Client requests are serviced by mapping keys onto buckets and looking up the corresponding server in an address table. Dynamic growth in terms of file size and access load is supported by bucket splits and bucket migration onto other existing or newly acquired servers. The significant and challenging problem addressed is how to achieve scalability so that both the file size and the client throughput can be scaled up by linearly increasing the number of servers and dynamically redistributing data. Unlike previous work with similar objectives, our data redistribution considers explicitly the cost/performance ratio of the system by aiming to minimize the number of servers that are acquired to provide the required performance. A new server is acquired only if the overall server utilization in the system does not drop below a specified threshold. Preliminary simulation results show that the goal of scalability with controlled cost/performance is indeed achieved to a large extent. } } @INPROCEEDINGS{ LABIO96 ,AUTHOR = "Wilburt Juan Labio and Hector Garcia-Molina" ,TITLE = "Efficient Snapshot Differential Algorithms for Data Warehousing" ,BOOKTITLE = "Proceedings of 22th International Conference on Very Large Data Bases" ,YEAR = "1996" ,month = "September" ,entered-by = "Arturo Crespo" ,abstract = { Detecting and extracting modifications from information sources is an integral part of data warehousing. For unsophisticated sources, in practice it is often necessary to infer modifications by periodically comparing snapshots of data from the source. Although this snapshot differential problem is closely related to traditional joins and outerjoins, there are significant differences, which lead to simple new algorithms. In particular, we present algorithms that perform (possibly lossy) compression of records. We also present a window algorithm that works very well if the snapshots are not ``very different.'' The algorithms are studied via analysis and an implementation of two of them; the results illustrate the potential gains achievable with the new algorithms. } ,privateComment = "This paper is probably too low level for the proposal." } @MISC{ WEIBEL95 ,AUTHOR = "Stuart Weibel and Jean Godby and Eric Miller and Ron Daniel" ,TITLE = "{OCLC/NCSA} Metadata Workshop Report" ,YEAR = "1995" ,month = "March" ,entered-by = "Arturo Crespo" ,notes="At http://www.oclc.org:5046/oclc/research/conferences/metadata/dublin_core_report.h tml" ,links = "(title:www:http://www.oclc.org:5046/oclc/research/conferences/metadata/dublin_c ore_report.html)" ,abstract = { This report defines the Dublin core. The Dublin core is a set of 13 metadata attributes that should be present in all documents. The attributes are: subject, title, author, publisher, other agent, date, object type, form, identifier, relation, source, language, coverage. } } @MISC{dcmi98 ,title = "The Dublin Core Metadata Initiative" ,year = "1998" ,howpublished = "http://purl.oclc.org/dc/" ,entered-by = "Andreas Paepcke" ,keywords = "dublin core, cataloging, metadata" ,abstract = {Minimal set of attributes} } @TECHREPORT{ LAGOZE96 ,AUTHOR = "Carl Lagoze and Clifford A. Lynch and Ron Daniel Jr." ,TITLE = "The {W}arwick Framework: A Container Architecture for Aggregating Sets of Metadata" ,INSTITUTION = "Cornell University" ,YEAR = "1996" ,month = "June" ,number = "TR96-1593" ,entered-by = "Arturo Crespo" ,abstract = { We describe a result of the June 1996 Warwick Metadata II Workshop. This Warwick Framework is a container architecture for aggregating logically, and perhaps physically, distinct packages of metadata. This architecture allows separate administration and access to metadata packages, provides for varying syntax in each package in conformance with semantic requirements, and it promotes interoperability and extensibility by allowing tools and agents to selectively access and manipulate individual packages and ignore others. At the conclusion of the paper we propose implementations of the Framework in HTML, MIME, SGML, and distributed objects } } @TECHREPORT{ LAGOZE95a ,AUTHOR = "Carl Lagoze and David Ely" ,TITLE = "Implementation Issues in an Open Architectural Framework for Digital Object Services" ,INSTITUTION = "Cornell University" ,YEAR = "1995" ,month = "September" ,number = "TR95-1590" ,entered-by = "Arturo Crespo" ,abstract = { We provide high level designs for implementing some key aspects of the Kahn/Wilensky Framework for Distributed Digital Object Services. We focus on five aspects of the architecture: 1) Negotiation on terms and conditions initiated by requests for stored digital objects. 2) Replication of handle server data and the notion of a primary handle server, 3) The mechanisms for replicating digital objects in multiple repositories and the assertions concerning such replication. 4) The meaning of mutable and immutable states for digital objects and the mechanisms for changing these states. 5) The basic services that the Repository Access Protocol (RAP) needs to support the infrastructure. } } @TECHREPORT{ LAGOZE95b ,AUTHOR = "Carl Lagoze and Robert McGrath and Ed Overly and Nancy Yeager" ,TITLE = "Implementation Issues in an Open Architectural Framework for Digital Object Services" ,INSTITUTION = "Cornell University" ,YEAR = "1995" ,month = "November" ,number = "TR95-1558" ,entered-by = "Arturo Crespo" ,abstract = { We describe a distributed object-based design for repositories in a digital library infrastructure. This design for Inter-operable Secure Object Stores, ISOS, defines the interfaces to secure repositories that inter-operate with each other, clients, and other services in the infrastructure. We define the interfaces to ISOS as class definitions in a distributed object system. We also define an extension to CORBA security that is used by repositories to secure access to themselves and their contained objects. } } @ARTICLE{MICHELLE96 ,AUTHOR = "Baldonado Michelle and Chen-Chuan K. Chang and Luis Gravano and Andreas Paepcke" ,TITLE = "The {S}tanford {D}igital {L}ibrary Metadata Architecture" ,JOURNAL = "International Journal of Digital Libraries" ,YEAR = "1997" ,note = "See also http://dbpubs.stanford.edu/pub/1997-71" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1997-71)" ,entered-by = "Andreas Paepcke" ,keywords = "metadata architecture" ,abstract = {~} } @MISC{ Smith96 ,AUTHOR = "Terence R. Smith and Steven Geffner and Jonathan Gottsegen" ,TITLE = "A General Framework for the Meta-Information and Catalogs in Digital Libraries" ,YEAR = "1996" ,entered-by = "Arturo Crespo" ,note = "At http://www.nml.org/resources/misc/metadata/proceedings/smith/ieee.html" ,abstract = { We present a general framework to support the modeling of digital documents and user queries in the context of digital libraries (DL's). The basis of the framework is a four-component model of a DL catalog involving a document modeling component, a query modeling component, a match component, and a catalog interoperability component. Meta-information in such a catalog provides models of library documents and facilitates efficient access to information represented in the documents. In particular, meta-information is conceptualized in terms of sets of relations between nominal representations of library documents and their properties, and sets of relations between document properties. The properties of the documents are modeled in meta-information in terms of a multiplicity of languages which vary between the catalog components and between catalogs. Each of the catalog components is modeled in terms of a set of formal systems related to the languages employed in the component. Using this framework, we discuss the two critical issues of catalog intraoperability and catalog interoperability. The framework provides a basis both for the rational design of meta-information and catalogs in DL contexts, and for an analysis and resolution of the intraoperability and interoperability issues. We provide examples of the issues discussed in terms of the Alexandria Digital Library. } } @BOOK{ CASTANO94 ,AUTHOR = "Silvana Castano and Maria Grazia Fugini and Giancarlo Martella and Pierangela Samarati" ,TITLE = "Database Security" ,PUBLISHER = "Addison-Wesley" ,YEAR = "1994" ,organization = "ACM" ,entered-by = "Arturo Crespo" ,abstract = { This is a comprehensive book on Database security. Chapter 1,2, and 3 describe information security, security models and security mechanisms and software from a general point of view. Chapter 4 gives a detail survey of Database security design. Chapter 5 explores the problem of security on statistical databases. Chapeter 6 describes different approaches in instrusion detection. Chapter 7 explores security models for next-generation databases (active db, oodb). } } @BOOK{ FERNANDEZ81 ,AUTHOR = "E. Fernandez and R. Summers and C. Wood" ,TITLE = "Database Security and Integrity" ,PUBLISHER = "Addison-Wesley" ,YEAR = "1981" ,entered-by = "Arturo Crespo" ,privateCOMMENT = "Recomended by Martin. Didn't read it. QA76.9.D3 F47 (in Math/CS and Jackson)" } @BOOK{ AMOROSO94 ,AUTHOR = "E. Amoroso" ,TITLE = "Fundamentals of Computer Security Technology" ,PUBLISHER = "Prentice Hall" ,YEAR = "1994" ,address = "Englewood Cliffs, NJ." ,entered-by = "Arturo Crespo" ,privateCOMMENT = "Recomended by Martin. Didn't read it. QA76.9.A25A46 (in Math/CS)" } @ARTICLE{ BRIN95 ,AUTHOR = "Sergev Brin and James Davis and Hector Garcia-Molina" ,TITLE = "Copy Detection Mechanisms for Digital Documents" ,JOURNAL = "SIGMOD" ,YEAR = "1995" ,pages = "398-409" ,entered-by = "Arturo Crespo" ,abstract = { In a digital library system, documents are available in digital form and therefore are more easily copied and their copyrights are more easily violated. This is a very serious problem, as it discourages owners of valuable information from sharing it with authorized users. There are two main philosophies for addressing this problem: prevention and detection. The former actually makes unauthorized use of documents difficult or impossible while the latter makes it easier to discover such activity. We propose a system for registering documents and then detecting copies, either complete copies or partial copies. We describe algorithms for such detection, and metrics required for evaluating detection mechanisms (covering accuracy, efficiency, and security). We also describe a working prototype, called COPS, describe implementation issues, and present experimental results that suggest the proper settings for copy detection parameters. } } @ARTICLE{ GARCIA96 ,AUTHOR = "Hector Garcia-Molina and Luis Gravano and Narayanan Shivakumar" ,TITLE = "dSCAM: Finding Document Copies Across Multiple Databases" ,JOURNAL = pdis96 ,YEAR = "1996" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1996-69)" ,entered-by = "Arturo Crespo" ,abstract = {} } @TECHREPORT{ MOCKAPETRIS87a ,AUTHOR = "P. Mockapetris" ,TITLE = "Domain Names - Concepts and Facilities" ,INSTITUTION = "Network Working Group" ,YEAR = "1987" ,month = "November" ,number = "RFC 1034" ,entered-by = "Arturo Crespo" ,note= "At http://info.internet.isi.edu/in-notes/rfc/files/rfc1034.txt" ,links = "(title:www:http://info.internet.isi.edu/in- notes/rfc/files/rfc1034.txt)" ,abstract = { Introduction to DNS, their use for Internet mail and host address support, and the protocols and servers used to implement domain name facilities. RFC 1035 provides implementation detail. RFC 1101 replaces it; however, without reading this, it's hard t understand RFC 1101. } } @TECHREPORT{ MOCKAPETRIS87b ,AUTHOR = "P. Mockapetris" ,TITLE = "Domain Names - Implementation and Specification" ,INSTITUTION = "Network Working Group" ,YEAR = "1987" ,month = "November" ,number = "RFC 1035" ,links = "(title:www:http://info.internet.isi.edu/in- notes/rfc/files/rfc1035.txt)" ,entered-by = "Arturo Crespo" ,note= "At http://info.internet.isi.edu/in-notes/rfc/files/rfc1035.txt" ,abstract = { Describes the details of the domain system and protocol (assumes one is familiar with RFC 1034. } } @TECHREPORT{ MOCKAPETRIS89 ,AUTHOR = "P. Mockapetris" ,TITLE = "DNS Encoding of Network Names and Other Types" ,INSTITUTION = "Network Working Group" ,YEAR = "1989" ,month = "April" ,number = "RFC 1101" ,entered-by = "Arturo Crespo" ,links = "(title:www:http://info.internet.isi.edu/in- notes/rfc/files/rfc1101.txt)" ,note= "At http://info.internet.isi.edu/in-notes/rfc/files/rfc1101.txt" ,abstract = { Presents 2 extensions to DNS: A specific method for entering and retrieving data records which map between network names and numbers. Ideas for a general method for describing mappings between arbitrary identifiers and numbers. One can't understand it w/o reading RFC 1034. Other RFCs related with DNS: 973, 1123, 1348. } } @TECHREPORT{ SOLLIS94 ,AUTHOR = "K. Sollins and L. Masinter" ,TITLE = "Functional Requirements for Uniform Resource Names" ,INSTITUTION = "Network Working Group" ,YEAR = "1994" ,month = "December" ,number = "RFC 1737" ,links = "(title:www:http://info.internet.isi.edu/in- notes/rfc/files/rfc1101.txt)" ,entered-by = "Arturo Crespo" ,note= "At http://info.internet.isi.edu/in-notes/rfc/files/rfc1101.txt" ,abstract = { This RFC introduces URNs. } } @TECHREPORT{ KAHN95 ,AUTHOR = "Robert Kahn and Robert Wilensky" ,TITLE = "A Framework for Distributed Digital Object Services" ,INSTITUTION = "CNRI" ,YEAR = "1995" ,month = "May" ,number = "tn95-01" ,links = "(title:www:http://WWW.CNRI.Reston.VA.US/home/cstr/arch/k-w.html)" ,entered-by = "Arturo Crespo" ,note = "At http://WWW.CNRI.Reston.VA.US/home/cstr/arch/k-w.html" ,abstract = { This paper provides a method for naming, identifying and/or invoking digital objects in a system of distributed repositories. It provides the foundation for the naming system of the CS-TR project. See also At http://WWW.CNRI.Reston.VA.US/home/cstr/arch/slides.html for a slide presentation. } } @ARTICLE{ COUSINS95 ,AUTHOR = "Steve B. Cousins and Steven P. Ketchpel and Andreas Paepcke and Hector Garcia-Molina and Scott W. Hassan and Martin R{\"{o}}scheisen" ,TITLE = "InterPay: Managing Multiple Payment Mechanisms in Digital Libraries" ,JOURNAL = "Digital Library" ,YEAR = "1995" ,entered-by = "Arturo Crespo" ,abstract = { Interpay paper } } @INPROCEEDINGS{ NEUMAN95 ,AUTHOR = "B.C. Neuman and G. Medvinsky" ,TITLE = "Requirements for network payment: The netcheque perspective" ,BOOKTITLE = "Proceedings of IEEE COMPCON" ,YEAR = "1995" ,month = "Mar" ,entered-by = "Arturo Crespo" ,abstract = { Secure methods of payment are needed before we will see widespread commercial use of the Internet. Recently proposed and implemented payment methods follow one of three models: electronic currency, credit-debit, and secure credit card transactions. Such payment services have different strengths and weaknesses with respect to the requirements of security, reliability, scalability, anonymity, acceptability, customer base, flexibility, convertibility, efficiency, ease of integration with applications, and ease of use. NetCheque is a payment system based on the credit-debit model. NetCheque is described and its strengths with respect to these requirements are discussed. } } @ARTICLE{ BOWMAN95 ,AUTHOR = "C.M. Bowman and Peter B. Danzig and Darren R. Hardy and Udi Manber and Michael F. Schwartz" ,TITLE = "The Harvest information discovery and access system" ,JOURNAL = "Computer Networks and ISDN Systems" ,YEAR = "1995" ,month = "December" ,volume = "28" ,number = "1-2" ,pages = "119-125" ,entered-by = "Arturo Crespo" ,abstract = { It is increasingly difficult to make effective use of Internet information, given the rapid growth in data volume, user base, and data diversity. We introduce Harvest, a system that provides a scalable, customizable architecture for gathering, indexing, caching, replicating, and accessing Internet information. } } @BOOK{ SALTON83 ,AUTHOR = "Gerard Salton" ,TITLE = "Introduction to modern information retrieval" ,PUBLISHER = "McGraw-Hill" ,YEAR = "1983" ,address= "New York" ,entered-by = "Arturo Crespo" ,abstract = { Math & Comp Sci/Green Z699.S313 } } @INPROCEEDINGS{ GRAVANO96 ,AUTHOR = "Luis Gravano and Chen-Chuan K. Chang and Hector Garcia-Molina and Andreas Paepcke" ,TITLE = "STARTS: Stanford Proposal for Internet Meta-Searching" ,BOOKTITLE = "Proc. of the 1997 ACM SIGMOD International Conference On Management of Data" ,YEAR = "1997" ,entered-by = "Arturo Crespo" } @MISC{ Schwartz96 ,editor = "Michael Schwartz" ,author = "Michael Schwartz" ,title = "Report of the Distributed Indexing/Searching Workshop" ,year = "1996" ,month = "May" ,howpublished = "url" ,note = "At http://www.w3.org/pub/WWW/Search/9605-Indexing-Workshop/" ,links = "(title:www:http://www.w3.org/pub/WWW/Search/9605-Indexing- Workshop/)" ,entered-by = "Arturo Crespo" } @BOOK{ WITTEN94 ,AUTHOR = "Ian H. Witten" ,TITLE = "Managing gigabytes : compressing and indexing documents and images" ,PUBLISHER = "Van Nostrand Reinhold" ,YEAR = "1994" ,address = "New York" ,entered-by = "Arturo Crespo" ,found-in = "TA1637.W58 1994 (Math/CS)" ,abstract = { A very good book in database compression. It describe first the mathematical foundations of compression. Then applies these concepts to data. This is followed by a study on how to compress indices. Finally, compression of databases of images is studied. The book include the description of a database system with the same name as the book. } } @ARTICLE{ FRENCH95 ,AUTHOR = "Jim French and Ed Fox and Kurt Maly and Alan Selman" ,TITLE = "Wide Area Technical Report Service: Technical Reports Online" ,JOURNAL = "Communications of the ACM" ,YEAR = "1995" ,month = "April" ,volume = "38" ,number = "4" ,pages = "45" ,entered-by = "Arturo Crespo" ,abstract = { This is the WATERS paper. } } @ARTICLE{ LAGOZE95 ,AUTHOR = "Carl Lagoze and Jim Davis" ,TITLE = "Dienst: An Architecture for Distributed Document Libraries" ,JOURNAL = "Communications of the ACM" ,YEAR = "1995" ,month = "April" ,volume = "38" ,number = "4" ,pages = "47" ,entered-by = "Arturo Crespo" ,abstract = { This is the DIENST paper } } @ARTICLE{ VanHeyningen94 ,AUTHOR = "Marc VanHeyningen" ,TITLE = "The Unified Computer Science Technical Report Index: Lessons in Indexing Diverse Resources" ,JOURNAL = "2nd International World Wide Web Conference, WWW'94" ,YEAR = "1994" ,month = "October" ,pages = "535-543" ,entered-by = "Arturo Crespo" ,abstract = {} } @INPROCEEDINGS{ YAN95 ,AUTHOR = "T. Yan and H. Garcia-Molina" ,TITLE = "{SIFT}---A tool for Wide-Area Information Dissemination" ,BOOKTITLE = "Proc. 1995 USENIX Technical Conference" ,YEAR = "1995" ,pages = "177-186" ,address = "New Orleans" ,note = "http://dbpubs.stanford.edu/pub/1994-7" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1994-7)" ,entered-by = "Arturo Crespo" ,keywords = "sift, digital library, selective dissemination, standing orders" ,abstract = {} } @BOOK{kicz91 ,AUTHOR = "Gregor Kiczales and Jim des Rivi\`{e}res and Daniel G. Bobrow" ,TITLE = "The Art of the Metaobject Protocol" ,PUBLISHER = "MIT Press" ,YEAR = "1991" ,entered-by = "Andreas Paepcke" ,keywords = "CLOS, MOP" ,abstract = {This is the official citation for the MOP spec. It can also be used as a citation for an intro to the *idea* of a MOP.} } @MISC{kicz94 ,author = "Gregor Kiczales and Andreas Paepcke" ,title = "Open Implementations and Metaobject Protocols" ,year = "1994" ,howpublished = "Expanded tutorial notes" ,note = "At http://db.stanford.edu/~paepcke/shared-documents/Tutorial.ps" ,links = "(title:www:http://db.stanford.edu/~paepcke/shared- documents/Tutorial.ps)" ,entered-by = "Andreas Paepcke" ,keywords = "metaobject protocol" ,abstract = {~} } @INCOLLECTION{nier93 ,author = "Oscar Nierstrasz" ,editor = "G. Agha, P. Wegner and A. Yonezawa" ,TITLE = "Composing Active Objects" ,BOOKTITLE = "Research Directions in Concurrent Object-Oriented Programming" ,PUBLISHER = "MIT Press" ,YEAR = "1993" ,pages = "151-171" ,entered-by = "Andreas Paepcke" ,keywords = "software components" ,abstract = {~} } @ARTICLE{salt84 ,AUTHOR = "J.H. Saltzer and D.P. Reed and D.D. Clark" ,TITLE = "End-to-End Arguments in System Design" ,JOURNAL = "ACM Transactions on Computer Systems" ,YEAR = "1984" ,month = "November" ,volume = "2" ,number = "4" ,pages = "277-288" ,entered-by = "Andreas Paepcke" ,abstract = {Argues that you should put functionality at the higher app layers, rather than at low layers. Includes a security example} } @ARTICLE{lee90 ,AUTHOR = "Jintae Lee and Thomas W. Malone" ,TITLE = "Partially Shared Views: A Scheme for Communicating among Groups that Use Different Type Hierarchies" ,JOURNAL = tois ,YEAR = "1990" ,month = "January" ,volume = "8" ,number = "1" ,entered-by = "Andreas Paepcke" ,found-in = "Paepcke's files" ,status = "skimmed" ,keywords = "object lens, information lens, group work, schema integration" ,abstract = {They use the type hierarchies to find maximally compatible types in interpreting mail messages. If both parties know about the fields in an `equipment-request', message recognition proceeds on that basis. If one of them only knows about `request' types, that coarser understanding is used.} } @INPROCEEDINGS{malo86 ,AUTHOR = "T.W. Malone and K.R. Grant and F. A. Turbak" ,TITLE = "The Information Lens: An intelligent system for information sharing in organizations" ,BOOKTITLE = chi86 ,YEAR = "1986" ,entered-by = "Andreas Paepcke" ,keywords = "Information lens" ,abstract = {This is the original Information Lens paper.} } @BOOK{silb91 ,AUTHOR = "A. Silberschatz and J. Peterson and P. Galvin" ,TITLE = "Operating System Concepts" ,PUBLISHER = "Addison Wesley" ,YEAR = "1991" ,entered-by = "Andreas Paepcke" ,found-in = "Hector's shelf" ,keywords = "operating systems, concurrency control" ,abstract = {Textbook} } @BOOK{ceri84 ,AUTHOR = "Stefano Ceri and Giuseppe Pelagatti" ,TITLE = "Distributed Databases" ,PUBLISHER = "McGraw-Hill, Inc." ,YEAR = "1984" ,entered-by = "Andreas Paepcke" ,found-in = "Hector's shelf" ,abstract = {Textbook} } @INPROCEEDINGS{keni96 ,AUTHOR = "Kenichi Kamiya and Martin R{\"{o}}scheisen and Terry Winograd" ,TITLE = "Grassroots: A System Providing a Uniform Framework for Communicating, Structuring, Sharing Information, and Organizing People" ,BOOKTITLE = www96 ,YEAR = "1996" ,note = "Also published in part as a short paper for CHI'96 (conference companion)" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1999-62)" ,entered-by = "Andreas Paepcke" ,keywords = "Grassroots, information dissemination, collaboration" ,abstract = {People keep pieces of information in diverse collections such as folders, hotlists, e-mail inboxes, newsgroups, and mailing lists. These collections mediate various types of collaborations including communicating, structuring, sharing information, and organizing people. Grassroots is a system that provides a uniform framework to support people's collaborative activities mediated by collections of information. The system seamlessly integrates functionalities currently found in such disparate systems as e-mail, newsgroups, shared hotlists, hierarchical indexes, hypermail, etc. Grassroots co-exists with these systems in that its users benefit from the uniform image provided by Grassroots, but other people can continue using other mechanisms, and Grassroots leverages from them. The current Grassroots prototype is based on an http-proxy implementation, and can be used with any Web browser. In the context of the design of a next-generation version of the Web, Grassroots demonstrates the utility of a uniform notification infrastructure. } } @INPROCEEDINGS{demi94 ,AUTHOR = "Giorgio De Michelis and M. Antonietta Grasso" ,TITLE = "Situating Conversations within the Language/Action Perspective: The {M}ilan Conversation Model" ,BOOKTITLE = cscw94 ,YEAR = "1994" ,entered-by = "Andreas Paepcke" ,found-in = "Terry Winograd's office" ,keywords = "Speech acts, multimedia conversations, collaboration" ,abstract = {~} } @INPROCEEDINGS{terr95 ,AUTHOR = "D.B. Terry and M.M. Theimer and K. Petersen and A.J. Demers and M.J. Spreitzer and C.H. Hauser" ,TITLE = "Managing update conflicts in Bayou, a weakly connected replicated storage system" ,BOOKTITLE = "Proceedings 15th Symposium on Operating Systems Principles" ,YEAR = "1995" ,month = "December" ,pages = "172-183" ,address = "Cooper Mountain, Colorado" ,entered-by = "Andreas Paepcke" ,note = "http://www.parc.xerox.com/bayou/" ,links = "(title:www:http://www.parc.xerox.com/bayou/)" ,keywords = "distributed updates, mobile operation, collaboration, weak consistency" ,abstract = {Main Bayou reference for Doug Terry's system. } } @INPROCEEDINGS{terr94 ,AUTHOR = "D.B. Terry and A.J. Demers and K. Petersen and M.J. Spreitzer and M.M. Theimer and B.B. Welch" ,TITLE = "Session guarantees for weakly consistent replicated data" ,BOOKTITLE = "Proceedings Third International Conference on Parallel and Distributed Information Systems" ,YEAR = "1994" ,month = "September" ,pages = "140-149" ,address = "Austin, Texas" ,note = "At http://www.parc.xerox.com/bayou/" ,links = "(title:www:http://www.parc.xerox.com/bayou/)" ,entered-by = "Andreas Paepcke" ,keywords = "distributed updates, mobile operation, collaboration, weak consistency" ,abstract = {~} } @INPROCEEDINGS{deme94 ,AUTHOR = "A.J. Demers and K. Petersen and M.J. Spreitzer and D.B. Terry and M.M. Theimer and B.B. Welch" ,TITLE = "The Bayou architecture: Support for data sharing among mobile users" ,BOOKTITLE = "Proceedings IEEE Workshop on Mobile Computing Systems \& Applications" ,YEAR = "1994" ,month = "December 8-9" ,pages = "2-7" ,address = "Santa Cruz, California" ,note = "At http://www.parc.xerox.com/bayou/" ,links = "(title:www:http://www.parc.xerox.com/bayou/)" ,entered-by = "Andreas Paepcke" ,keywords = "distributed updates, mobile operation, collaboration, weak consistency" ,abstract = {~} } @INPROCEEDINGS{lam96 ,AUTHOR = "W. Lam and S. Mukhopadhyay and J. Mostafa and M. Palakal" ,TITLE = "Detection of Shifts in User Interests for Personalized Information Filtering" ,BOOKTITLE = sigir96 ,YEAR = "1996" ,publisher = "ACM" ,entered-by = "Andreas Paepcke" ,keywords = "filtering, standing orders" ,abstract = {~} } @ARTICLE{bala95 ,AUTHOR = "Marko Balabanovic and Yoav Shoham and Yeogirl Yun" ,TITLE = "An Adaptive Agent for Automated Web Browsing" ,JOURNAL = "Journal of Visual Communication and Image Representation" ,YEAR = "1995" ,month = "December" ,volume = "6" ,number = "4" ,entered-by = "Andreas Paepcke" ,keywords = "agents, digital library" ,abstract = {you give agent profile. It looks at the Web for things of interest and reports back. You give feedback} } @ARTICLE{bala97 ,AUTHOR = "Marko Balabanovic and Yoav Shoham" ,TITLE = "Combining Content-Based and Collaborative Recommendation" ,JOURNAL = cacm ,YEAR = "1997" ,month = "March" ,volume = "40" ,number = "3" ,entered-by = "Andreas Paepcke" ,keywords = "FAB" ,abstract = {~} } @ARTICLE{gold92 ,AUTHOR = "D. Goldberg and D. Nichols and B.M. Oki and D. Terry" ,TITLE = "Using Collaborative Filtering to Weave an Information Tapestry" ,JOURNAL = cacm ,YEAR = "1992" ,month = dec ,volume = "35" ,number = "12" ,pages = "61-70" ,entered-by = "Andreas Paepcke" ,keywords = "collaborative filtering, tapestry" ,abstract = {use user annotations to help with filtering.} } @INPROCEEDINGS{resn94 ,AUTHOR = "P. Resnick and N. Iacovou and M. Suchak and P. Bergstrom and J. Riedl" ,TITLE = "Group{L}ens: an Open Architecture for Collaborative Filtering of Netnews" ,BOOKTITLE = cscw94 ,YEAR = "1994" ,entered-by = "Andreas Paepcke" ,keywords = "collaborative filtering, value filtering" ,abstract = {~} } @INPROCEEDINGS{mack95 ,AUTHOR = "Jock D. Mackinlay and Ramana Rao and Stuart K. Card" ,TITLE = "An Organic User Interface for Searching Citation Links" ,BOOKTITLE = chi95 ,YEAR = "1995" ,entered-by = "Andreas Paepcke" ,keywords = "Butterfly, citation web" ,abstract = {Crawls a citation index db and builds a 3D graph. Includes app for exploring the graph} } @INPROCEEDINGS{paep89c ,AUTHOR = "Andreas Paepcke" ,TITLE = "{PCLOS}: {A} {C}ritical {R}eview" ,BOOKTITLE = oopsla89 ,YEAR = "1989" ,links = "(title:www:http://db.stanford.edu/~paepcke/shared-documents/pclos- critical.ps)" ,entered-by = "Andreas Paepcke" ,keywords = "PCLOS, object servers, object persistence" ,abstract = {Uses PCLOS as a roadmap through issues of obj persistence. This replaces paep89b, which is the techreport edition.} } @INPROCEEDINGS{paep88a ,AUTHOR = "Andreas Paepcke" ,TITLE = "{PCLOS}: {A} {F}lexible {I}mplementation of {CLOS} {P}ersistence" ,BOOKTITLE = ecoop88 ,YEAR = "1988" ,editor = "S. Gjessing and K. Nygaard" ,publisher = "Lecture Notes in Computer Science, Springer Verlag" ,links = "(title:www:http://db.stanford.edu/~paepcke/shared-documents/pclos- report.ps)" ,entered-by = "Andreas Paepcke" ,keywords = "PCLOS, object persistence" ,abstract = {pages: 374-389} } @INPROCEEDINGS{paep93a ,AUTHOR = "Andreas Paepcke" ,TITLE = "An Object-Oriented View Onto Public, Heterogeneous Text Databases" ,BOOKTITLE = icde93 ,YEAR = "1993" ,links = "(title:www:http://db.stanford.edu/~paepcke/shared- documents/dialog.ps)" ,entered-by = "Andreas Paepcke" ,keywords = "Dialog, schema integration, multidatabases" ,abstract = {This describes the model of the interface to Dialog} } @INPROCEEDINGS{wied86 ,AUTHOR = "Fred Friedman and Arthur M. Keller and Gio Wiederhold and Mike R. Berkowitz and John Salasin and David L. Spooner" ,TITLE = "Reference Model for {ADA} Interfaces to Database Management Systems" ,BOOKTITLE = "Proceedings Second IEEE Computer Society Data Engineering Conference" ,YEAR = "1986" ,entered-by = "Andreas Paepcke" ,keywords = "DADAISM" ,abstract = {~} } @INPROCEEDINGS{blak93 ,AUTHOR = "J.A. Blakeley and W.J. McKenna and G. Graefe" ,TITLE = "Experiences building the Open OODB query optimizer" ,BOOKTITLE = sigmod93 ,YEAR = "1993" ,entered-by = "Andreas Paepcke" ,keywords = "open oodb, open implementations" ,abstract = {The authors report their experiences building the query optimizer for TI's Open OODB system. It is probably the first working object query optimizer to be based on a complete extensible optimization framework including logical algebra, execution algorithms, property enforcers, logical transformation rules, implementation rules, and selectivity and cost estimation. Their algebra incorporates a new materialize operator with its corresponding logical transformation and implementation rules that enable the optimization of path expressions. The Open OODB query optimizer was constructed using the Volcano Optimizer Generator, demonstrating that this second-generation optimizer generator enables rapid development of efficient and effective query optimizers for non-standard data models and systems.} } @INPROCEEDINGS{bald97a ,AUTHOR = "Michelle Baldonado and Chen-Chuan K. Chang and Luis Gravano and Andreas Paepcke" ,TITLE = "Metadata for Digital Libraries: Architecture and Design Rationale" ,BOOKTITLE = dl97 ,YEAR = "1997" ,note = "At http://dbpubs.stanford.edu/pub/1997-26" ,pages = "47--56" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1997-26)" ,entered-by = "Andreas Paepcke" ,keywords = "metadata" ,abstract = {In a distributed, heterogeneous, proxy-based digital library, autonomous services and collections are accessed indirectly via proxies. To facilitate metadata compatibility and interoperability in such a digital library, we have designed a metadata architecture that includes four basic component classes: attribute model proxies, attribute model translators, metadata facilities for search proxies, and metadata repositories. Attribute model proxies elevate both attribute sets and the attributes they define to first-class objects. They also allow relationships among attributes to be captured. Attribute model translators map attributes and attribute values from one attribute model to another (where possible). Metadata facilities for search proxies provide structured descriptions both of the collections to which the search proxies provide access and of the search capabilities of the proxies. Finally, metadata repositories accumulate selected metadata from local instances of the other three component classes in order to facilitate global metadata queries and local metadata caching. In this paper, we outline further the roles of these component classes, discuss our design rationale, and analyze related work. } } @ARTICLE{bald97b ,AUTHOR = "Michelle Baldonado" ,TITLE = "Searching, Browsing, and Metasearching with SenseMaker" ,JOURNAL = "Web Techniques Magazine" ,YEAR = "1997" ,month = "May" ,entered-by = "Andreas Paepcke" ,keywords = "sensemaker" ,abstract = {~} } @INPROCEEDINGS{ketc97 ,AUTHOR = "Steven P. Ketchpel and Hector Garcia-Molina and Andreas Paepcke" ,TITLE = "Shopping Models: A Flexible Architecture for Information Commerce" ,BOOKTITLE = dl97 ,YEAR = "1997" ,note = "At http://dbpubs.stanford.edu/pub/1997-52" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1997-52)" ,entered-by = "Andreas Paepcke" ,keywords = "payment, electronic commerce, shopping models" ,abstract = {In a digital library, there are many different interaction models between customers and information providers or merchants. Subscriptions, sessions, pay-per-view, shareware, and pre-paid vouchers are different models that each have different properties. A single merchant may use several of them. Yet if a merchant wants to support multiple models, there is a substantial amount of work to implement each one. In this paper, we formalize the shopping models which represent these different modes of consumer to merchant interaction. In addition to developing the overall architecture, we define the application program interfaces (API) to interact with the models. We show how a small number of primitives can be used to construct a wide range of shopping models that a digital library can support, and provide examples of the shopping models in operation, demonstrating their flexibility. } } @TECHREPORT{cous97 ,AUTHOR = "Steve B. Cousins and Andreas Paepcke and Scott W. Hassan and Terry Winograd" ,TITLE = "Towards Wide-Area Distributed Interfaces" ,INSTITUTION = "Stanford University" ,YEAR = "1997" ,number = "SIDL-WP-1996-0037; 1997-67" ,note = "At http://dbpubs.stanford.edu/pub/1997-67" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1997-67)" ,entered-by = "Andreas Paepcke" ,keywords = "DLITE, distributed interface" ,abstract = {We have designed and prototyped a series of interfaces for Digital Libraries. These interfaces use CORBA objects to distribute interface modeling and rendering across machines. We describe the design tensions arising in the context of such distribution, locate existing UI technology in the resulting design space, and explain the location of our final prototype in that space. We view Digital Libraries as collections of repositories and publication-related services that may be distributed over large distances and must be accessible from many locations and through multiple hardware, software, and networking platforms. We describe our use of CORBA and briefly introduce a drag-and-drop interface developed to provide unified access to heterogeneous Digital Library resources.} } @article{yan-bool, author = "T.W. Yan and H. Garcia-Molina", title = "Index Structures for Selective Dissemination of Information Under the Boolean Model", journal = "{ACM Transactions} on Database Systems", volume = "19", number = "2", pages = "332-64", year = "1994" } @Inproceedings{yan-dsdi, author = "T.W. Yan and H. Garcia-Molina", title = "Distributed Selective Dissemination of Information", booktitle = "Proc. Parallel and Distributed Information Systems", year = "1994", pages = "89-98" } @INPROCEEDINGS{papa95 ,AUTHOR = "Yannis Papakonstantinou and Hector Garcia-Molina and Jennifer Widom" ,TITLE = "Object Exchange Across Heterogeneous Information Sources" ,BOOKTITLE = icde95 ,YEAR = "1995" ,address = "Taiwan" ,pages = "251-260" ,entered-by = "Andreas Paepcke" ,keywords = "OEM" ,abstract = {~} } @INPROCEEDINGS{papa95a ,AUTHOR = "Yannis Papakonstantinou and Hector Garcia-Molina and Ashish Gupta and Jeffrey Ullman" ,TITLE = "A Query Translation Scheme for Rapid Implementation of Wrappers" ,BOOKTITLE = "Fourth International Conference on Deductive and Object-Oriented Databases" ,YEAR = "1995" ,address = "National University of Singapore(NUS), Singapore" ,pages = "161-186" ,entered-by = "Andreas Paepcke" ,keywords = "Mediator generation" ,abstract = {~} } @INPROCEEDINGS{papa96 ,AUTHOR = "Yannis Papakonstantinou and Serge Abiteboul and Hector Garcia- Molina" ,TITLE = "Object Fusion in Mediator Systems" ,BOOKTITLE = vldb96 ,YEAR = "1996" ,pages = "413-424" ,entered-by = "Andreas Paepcke" ,keywords = "Mediators" ,abstract = {~} } @INPROCEEDINGS{labi96 ,AUTHOR = "Wilburt Labio and Hector Garcia-Molina" ,TITLE = "Efficient Snapshot Differential Algorithms for Data Warehousing" ,BOOKTITLE = vldb96 ,YEAR = "1996" ,pages = "63-74" ,entered-by = "Andreas Paepcke" ,keywords = "data warehousing, warehouse update, cache consistency" ,abstract = {~} } @ARTICLE{moli95 ,AUTHOR = "H. Garcia-Molina and J. Hammer and J. Widom and W. Labio and Y. Zhuge" ,TITLE = "The Stanford Data Warehousing Project" ,JOURNAL = "IEEE Data Engineering Bulletin" ,YEAR = "1995" ,month = "June" ,volume = "18" ,number = "2" ,pages = "41-48" ,entered-by = "Andreas Paepcke" ,keywords = "data warehousing" ,abstract = {~} } @INPROCEEDINGS{zhug95 ,AUTHOR = "Yue Zhuge and Hector Garcia-Molina and Joachim Hammer and Jennifer Widom" ,TITLE = "View Maintenance in a Warehousing Environment" ,BOOKTITLE = "SIGMOD Conference" ,YEAR = "1995" ,month = "May" ,pages = "316-327" ,entered-by = "Andreas Paepcke" ,keywords = "views, data warehousing" ,abstract = {~} } @BOOK{wino87 ,AUTHOR = "Terry Winograd and Fernando Flores" ,TITLE = "Understanding Computers and Cognition: A New Foundation for Design" ,PUBLISHER = "Addison-Wesley" ,YEAR = "1987" ,entered-by = "Andreas Paepcke" ,keywords = "" ,abstract = {~} } @BOOK{adle92 ,EDITOR = "Paul S. Adler and Terry Winograd" ,TITLE = "Usability : turning technologies into tools" ,PUBLISHER = "Oxford University Press" ,YEAR = "1992" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @BOOK{wino96 ,EDITOR = "Terry Winograd" ,TITLE = " Bringing Design to Software" ,PUBLISHER = "Addison-Wesley" ,YEAR = "1996" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @INPROCEEDINGS{shet93 ,AUTHOR = "B. Sheth and P. Maes" ,TITLE = "Evolving Agents for Personalized Information Filtering" ,BOOKTITLE = "Proceedings of the Ninth Conference on Artificial Intelligence for Applications" ,YEAR = "1993" ,publisher = "IEEE Computer Society Press" ,entered-by = "Andreas Paepcke" ,keywords = "agents, learning, filters, net news" ,abstract = {Describes how techniques from artificial life can be used to evolve a population of personalized information filtering agents. The technique of artificial evolution and the technique of learning from feedback are combined to develop a semi-automated information filtering system which dynamically adapts to the changing interests of the user. Results of a set of experiments are presented in which a small population of information filtering agents was evolved to make a personalized selection of news articles from the USENET newsgroups. The results show that the artificial evolution component of the system is responsible for improving the recall rate of the selected set of articles, while learning from feedback component improves the precision rate.} } @ARTICLE{maes94b ,AUTHOR = "P. Maes" ,TITLE = "Agents that Reduce Work and Information Overload." ,JOURNAL = cacm ,YEAR = "1994" ,month = "July" ,volume = "37" ,number = "7" ,pages = "31-40" ,entered-by = "Andreas Paepcke" ,keywords = "mail agents" ,abstract = {The currently dominant interaction metaphor of direct manipulation requires the user to initiate all tasks explicitly and to monitor all events. This metaphor will have to change if untrained users are to make effective use of the computer and networks of tomorrow. Techniques from the field of AI, in particular so-called "autonomous agents", can be used to implement a complementary style of interaction, which has been referred to as indirect management. Instead of user-initiated interaction via commands and or direct manipulation, the user is engaged in a cooperative process in which human and computer agents both initiate communication, monitor events and perform tasks. The metaphor used is that of a personal assistant who is collaborating with the user in the same work environment. The assistant becomes gradually more effective as it learns the user's interests, habits and preferences (as well as those of his or her community). Novice that the agent is not necessarily an interface between the computer and the user. In fact, the most successful interface agents are those that do not prohibit the user from taking actions and fulfilling tasks personally. This article focuses on a novel approach to building interface agents. It presents results from several prototype agents that have been built using this approach, including agents that provide personalized assistance with meeting scheduling, e-mail handling, electronic news filtering and selection of entertainment} } @INPROCEEDINGS{maes94a ,AUTHOR = "P. Maes" ,TITLE = "Scial Interface Agents: Acquiring Competence by Learning from Users and Other Agents" ,BOOKTITLE = "Proceedings of AAAI Spring Symposium Series" ,YEAR = "1994" ,entered-by = "Andreas Paepcke" ,abstract = {Interface agents are computer programs that employ artificial intelligence techniques in order to provide assistance to a user dealing with a particular computer application. The paper discusses an interface agent which has been modeled closely after the metaphor of a personal assistant. The agent learns how to assist the user by (i) observing the user`s actions and imitating them. (ii) Receiving user feedback when it takes wrong action. (iii) Being trained by the user on the basis of hypothetical examples and (iv) learning from other agents that assist other users with the same task. The paper discusses how this learning agent was implemented using memory-based learning and reinforcement learning techniques. It presents actual results from two prototype agents built using these techniques: one for a meeting scheduling application and one for electronic mail. It argues that the machine learning approach to building interface agents is a feasible one which has several advantages over other approaches: it provides a customized and adaptive solution which is less costly and ensures better user acceptability } } @INPROCEEDINGS{maes95 ,AUTHOR = "Upendra Shardanand and Pattie Maes" ,TITLE = "Social Information Filtering: Algorithms for Automating 'Word of Mouth'" ,BOOKTITLE = chi95 ,YEAR = "1995" ,publisher = "Addison-Wesley" ,entered-by = "Andreas Paepcke" ,keywords = "value filtering, social filtering, search" ,abstract = {} } @ARTICLE{wino87a ,AUTHOR = "Terry Winograd" ,TITLE = "A Language/Action Perspective on the Design of Cooperative Work" ,JOURNAL = "Human-Computer Interaction" ,YEAR = "1995" ,volume = "3" ,number = "1" ,entered-by = "Andreas Paepcke" ,abstract = {In creating computer-based systems, one works within a perspective that shapes the design questions that will be asked and the kinds of solutions that are sought. The article introduces a perspective based on language as action, and explores its consequences for system design. The author describes a communication too called The Coordinator, which was designed from a language/action perspective; and suggests how further aspects of coordinated work might be addressed in a similar style. The language/action perspective is illustrated with an example based on studies of nursing work in a hospital ward and contrasted to other currently prominent perspectives } } @BOOK{tanenbaum ,AUTHOR = "Andrew S. Tanenbaum" ,TITLE = "Distributed Operating Systems" ,PUBLISHER = "Prentice Hall" ,YEAR = "1995" ,address = "Englewood Cliffs, NJ" ,entered-by = "hector" } @ARTICLE{sheth ,AUTHOR = "D. Georgakopoulos and M. Hornick and A. Sheth" ,TITLE = "An Overview of Workflow Management: From Process Modeling to Infrastructure for Automation" ,JOURNAL = "Journal on Distributed and Parallel Database Systems" ,YEAR = "1995" ,volume = "3" ,number = "2" ,entered-by = "hector" } @ARTICLE{sheth2 ,AUTHOR = "John A. Miller and Amit P. Sheth and Krys J. Kochut and Xuzhong Wang" ,TITLE = "CORBA-Based Run-Time Architectures for Workflow Management Systems" ,JOURNAL = "Journal of Database Management, Special Issue on Multidatabases" ,YEAR = "1996" ,volume = "7" ,number = "1" ,pages = "16--27" ,entered-by = "hector" } @ARTICLE{willy ,AUTHOR = "David B. Johnson and Willy E. Zwaenepoel" ,TITLE = "Recovery in distributed systems using optimistic message logging and checkpointing" ,JOURNAL = "Journal of Algorithms" ,YEAR = "1990" ,month= "September" ,volume = "11" ,number = "3" ,pages = "462--491" ,entered-by = "hector" } @MISC{coalition ,key = "workflow management coalition" ,title = "The {Workflow} {Management} {Coalition} Home Page" ,note = "At http://www.aiim.org/wfmc/mainframe.htm" ,links = "(title:www:http://www.aiim.org/wfmc/mainframe.htm)" ,entered-by = "hector" } @PROCEEDINGS{workflow ,key = "Sheth" ,editor = "Amit Sheth" ,title = "Proceedings {NSF} {Workshop} on Workflow and Process Automation in Information Systems: State-of-the-art and Future Directions" ,month = "May" ,year = "1996" ,address = "Athens, Georgia" ,note = "At http:://lsdis.cs.uga.edu/activities/NSF-workflow/" ,entered-by = "hector" } @INPROCEEDINGS{chan97 ,AUTHOR = "Chen-Chuan K. Chang and Hector Garcia-Molina" ,TITLE = "Evaluating the Cost of Boolean Query Mapping" ,BOOKTITLE = dl97 ,YEAR = "1997" ,note = "At http://dbpubs.stanford.edu/pub/1997-25" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1997-25)" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @INPROCEEDINGS{koll97 ,AUTHOR = "D. Koller and M. Sahami" ,TITLE = "Hierarchically Classifying Documents Using Very Few Words" ,BOOKTITLE = "Proceedings of the Fourteenth International Conference on Machine Learning (ICML-97)" ,YEAR = "1997" ,entered-by = "Andreas Paepcke" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1997-75)" ,keywords = "categorization, clustering" ,abstract = {The proliferation of topic hierarchies for text documents has resulted in a need for tools that automatically classify new documents within such hierarchies. One can use existing classifiers by ignoring the hierarchical structure, treating the topics as separate classes. Unfortunately, in the context of text categorization, we are faced with a large number of classes and a huge number of relevant features needed to distinguish between them. Consequently, we are restricted to using only very simple classifiers, both because of computational cost and the tendency of complex models to overfit. We propose an approach that utilizes the hierarchical topic structure to decompose the classification task into a set of simpler problems, one at each node in the classification tree. As we show, each of these smaller problems can be solved accurately by focusing only on a very small set of features, those relevant to the task at hand. This set of relevant features varies widely throughout the hierarchy, so that, while the overall relevant feature set may be large, each classifier only examines a small subset. The use of reduced feature sets allows us to utilize more complex (probabilistic) models, without encountering the computational and robustness difficulties described above.} } , "Responsive Interaction for a Large Web Application: The Meteor Shower Architecture in the WebWriter II Editor." @INPROCEEDINGS{cres97 ,AUTHOR = "Arturo Crespo and Bay-Wei Chang and Eric A. Bier" ,TITLE = "Responsive Interaction for a Large Web Application: The Meteor Shower Architecture in the {W}eb{W}riter {II} Editor" ,BOOKTITLE = www97 ,YEAR = "1997" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1997-35)" ,entered-by = "Andreas Paepcke" ,abstract = {Traditional server-based web applications allow access to server-hosted resources, but often exhibit poor responsiveness due to server load and network delays. Client-side web applications, on the other hand, provide excellent interactivity at the expense of limited access to server resources. The WebWriter II Editor, a direct manipulation HTML editor that runs in a web browser, uses both server-side and client-side processing in order to achieve the advantages of both. In particular, this editor downloads the document data structure to the browser and performs all operations locally. The user interface is based on HTML frames and includes individual frames for previewing the document and displaying general and specific control panels. All editing is done by JavaScript code residing in roughly twenty HTML pages that are downloaded into these frames as needed. Such a client-server architecture, based on frames, client-side data structures, and multiple JavaScript-enhanced HTML pages appears promising for a wide variety of applications. This paper describes this architecture, the Meteor Shower Application Architecture, and its use in the WebWriter II Editor.} } @INPROCEEDINGS{ketc96a ,AUTHOR = "Steven Ketchpel and Hector Garcia-Molina and Andreas Paepcke and Scott Hassan and Steve Cousins" ,TITLE = "{UPAI}: A Universal Payment Application Interface" ,BOOKTITLE = "USENIX 2nd e-commerce workshop" ,YEAR = "1996" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1996-8)" ,entered-by = "Andreas Paepcke" ,keywords = "upai, commerce, payment" ,abstract = {~} } @MISC{ketc97a ,author = "Steven Ketchpel" ,title = "Distributed Commerce Transactions with Timing Deadlines and Direct Trust" ,year = "1997" ,howpublished = "Poster at International Joint Conference on AI'97" ,entered-by = "Andreas Paepcke" ,keywords = "distributed trust" ,abstract = {~} } @INPROCEEDINGS{bala97a ,AUTHOR = "Marko Balabanovic" ,TITLE = "An Adaptive Web Page Recommendation Service" ,BOOKTITLE = "Proceedings of the First International Conference on Autonomous Agents p. 378-385" ,YEAR = "1997" ,month = "February" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-40)" ,entered-by = "Andreas Paepcke" ,keywords = "fab" ,abstract = {~} } @TECHREPORT{chan96c ,AUTHOR = "Edward Chang and Hector Garcia-Molina" ,TITLE = "Minimizing Memory Requirements In Media Servers" ,INSTITUTION = "Stanford University" ,YEAR = "1996" ,month = dec ,number = "SIDL-WP-1996-0045; 1996-4" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1996-4)" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @INPROCEEDINGS{koha96 ,AUTHOR = "Ron Kohavi and Mehran Sahami" ,TITLE = "Error-Based and Entropy-Based Discretization of Continuous Features" ,BOOKTITLE = "Second International Conference on Knowledge Discovery in Databases" ,YEAR = "1996" ,note = "At ftp://starry.stanford.edu/pub/sahami/papers/kdd96-disc.ps" ,links = "(title:www:ftp://starry.stanford.edu/pub/sahami/papers/kdd96- disc.ps)" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @ARTICLE{koll96a ,AUTHOR = "D.Koller and Y. Shoham" ,TITLE = "Information agents: A new challenge for {AI}" ,JOURNAL = "IEEE Expert" ,YEAR = "1996" ,month = "June" ,pages = "8-10" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @INPROCEEDINGS{saha96 ,AUTHOR = "M. Sahami and M. Hearst and E. Saund" ,TITLE = "Applying the Multiple Cause Mixture Model to Text Categorization" ,BOOKTITLE = "Proceedings of the Thirteenth International Conference on Machine Learning" ,YEAR = "1996" ,pages = "435-443" ,publisher = "Morgan Kaufmann" ,note = "At http://dbpubs.stanford.edu/pub/1996-78" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1996-78)" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @INPROCEEDINGS{saha96a ,AUTHOR = "Mehran Sahami" ,TITLE = "Learning Limited Dependence {B}ayesian Classifiers" ,BOOKTITLE = "Second International Conference on Knowledge Discovery in Databases" ,YEAR = "1996" ,note = "At ftp://starry.stanford.edu/pub/sahami/papers/kdd96-learn-bn.ps" ,links = "(title:www:ftp://starry.stanford.edu/pub/sahami/papers/kdd96-learn- bn.ps)" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @INPROCEEDINGS{saha97 ,AUTHOR = "Mehran Sahami and Salim Yusufali and Michelle Q. Wang Baldonado" ,TITLE = "Real-time Full-text Clustering of Networked Documents" ,BOOKTITLE = "AAAI-97, Proceedings of the Fourteenth National Conference on Artificial Intelligence" ,YEAR = 1997 ,entered-by = "Andreas Paepcke" ,keywords = "clustering" ,abstract = {We describe a initial results with a service for clustering networked documents that has been successfully integrated into the Stanford Digital Libraries Testbed.} } @TECHREPORT{twid96 ,AUTHOR = "M.B. Twidale and D.M. Nichols and C.D. Paice" ,TITLE = "Browsing is a Collaborative Processs" ,INSTITUTION = "Computing Dept., Lancaster University" ,YEAR = "1996" ,number = "Technical Report CSEG/1/96" ,links = "(title:www:http://www.comp.lancs.ac.uk/computing/research/cseg/projects/ariadne /docs/bcp.html)" ,entered-by = "Steve Cousins" ,keywords = "collaboration" ,abstract = {Interfaces to databases have traditionally been designed as single-user systems that hide other users and their activity. This paper aims to show that collaboration is an important aspect of searching online information stores that requires explicit computerised support. The claim is made that a truly user-centred system must acknowledge and support collaborative interactions between users. Collaborative working implies a need to share information: both the search product and the search process. Searches need not be restricted to inanimate resources but people can also search for other people. The ARIADNE system is introduced as an example of computerised support for collaboration between browsers. A number of systems offering varied approaches to supporting collaboration are surveyed and a structure for analysing the various aspects of collaboration is applied. } } @ARTICLE{NotkinHS+87 ,AUTHOR = "David Notkin and Norman Hutchinson and Jan Sanislo and Michael Schwartz" ,TITLE = "Heterogeneous Computing Environments: Report on the ACM SIGOPS Workshop on Accommodating Heterogeneity" ,JOURNAL = cacm ,YEAR = "1987" ,month = Feb ,volume = "30" ,number = "2" ,pages = "24--32" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {This paper reports a workshop conducted in December 1985 as a forum for an international group of fifty researchers to discuss the technical issues surrounding heterogeneous computing environments. In particular, it discusses five basic topics of heterogeneity: interconnection, filing, authentication, naming, and user interfaces. } } @ARTICLE{SiegelDA96 ,AUTHOR = "Howard Jay Siegel and Henry G. Dietz and John K. Antonio" ,TITLE = "Software Support for Heterogeneous Computing" ,JOURNAL = csurvey ,YEAR = 1996 ,month = Mar ,volume = 28 ,number = 1 ,pages = "237--239" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {Part of ACM Computing Surveys' special issue on Perspectives in Computer Science. Describes supports necessary for executing subtasks on different machines with diverse execution environments.} } @ARTICLE{Wegner96 ,AUTHOR = "Peter Wegner" ,TITLE = "Interoperability" ,JOURNAL = csurvey ,YEAR = 1996 ,month = Mar ,volume = 28 ,number = 1 ,pages = "285--287" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {Part of ACM Computing Surveys' special issue on Perspectives in Computer Science. Discusses various aspects of interoperability-- the ability of two or more software components to cooperate despite differences in language, interface, and execution platforms. In particular, this paper focuses on client-server interoperability.} } @ARTICLE{Manola95 ,AUTHOR = "Frank Manola" ,TITLE = "Interoperability Issues in Large-Scale Distributed Object Systems" ,JOURNAL = csurvey ,YEAR = 1995 ,month = Jun ,volume = 27 ,number = 2 ,pages = "268--270" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {Focuses on enterprise-wide client/server systems being developed to support operational computing within large organizations to illustrate interoperability issues.} } @ARTICLE{DayZimmermann83 ,AUTHOR = "J.D. Day and H. Zimmermann" ,TITLE = "The OSI Reference Model" ,JOURNAL = "Proc. of the IEEE" ,YEAR = 1983 ,month = Dec ,volume = 71 ,pages = "1334--1340" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {~} } @BOOK{Tanenbaum89 ,AUTHOR = "Andrew S. Tanenbaum" ,TITLE = "Computer Networks, 2nd Ed." ,PUBLISHER = "Prentice-Hall" ,YEAR = 1989 ,address = "Englewood Cliffs, NJ" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {Chapter 1 (Introduction) provides a good discussion on the OSI reference model, and the network standardization issues.} } @ARTICLE{BrightHP92 ,AUTHOR = "M.W. Bright and A.R. Hurson and Simin H. Pakzad" ,TITLE = "A Taxonomy and Current Issues in Multidatabase Systems" ,JOURNAL = ieeecomp ,YEAR = 1992 ,month = Mar ,volume = 25 ,number = 3 ,pages = "51--60" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {This article presents a taxonomy of global information-sharing systems and discusses where multidatabase systems fit in the spectrum of solutions. The authors use this taxonomy as a basis for defining multidatabase systems, then discuss the issues associated with them. In particular, the paper focuses on two major design approaches-- global schema systems and multidatabase language systems.} } @ARTICLE{ShethLarson90 ,AUTHOR = "Amit P. Sheth and James A. Larson" ,TITLE = "Federated Database Systems for Managing Distributed, Heterogeneous, and Autonomous Databases" ,JOURNAL = csurvey ,YEAR = 1990 ,month = Sep ,volume = 22 ,number = 3 ,pages = "183--236" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {This paper defines a reference architecture for distributed database management systems from system and schema viewpoints and shows how various federated database systems (FDBS) can be developed. It then define a methodology for developing one of the popular architectures of an FDBS. Finally, it discusses critical issues related to developing and operating FDBS.} } @ARTICLE{ThomasTC+90 ,AUTHOR = "Gomer Thomas and Glenn R. Thompson and Chin-Wan Chung and Edward Barkmeyer and Fred Carter and Marjorie Templeton and Stephen Fox and Berl Hartman" ,TITLE = "Heterogeneous Distributed Database Systems for Production Use" ,JOURNAL = csurvey ,YEAR = 1990 ,month = Sep ,volume = 22 ,number = 3 ,pages = "237--266" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {A survey of the state of the art in heterogeneous distributed database systems targeted for production environments.} } @ARTICLE{LitwinMR90 ,AUTHOR = "Witold Litwin and Leo Mark and Nick Roussopoulos" ,TITLE = "Interoperability of Multiple Autonomous Databases" ,JOURNAL = csurvey ,YEAR = 1990 ,month = Sep ,volume = 22 ,number = 3 ,pages = "267--293" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {Discusses the approach of multidatabase or federated systems, which make databases interoperable, i.e., usable without a globally integrated schema.} } @ARTICLE{Wiederhold95 ,AUTHOR = "Gio Wiederhold" ,TITLE = "Mediation in Information Systems" ,JOURNAL = csurvey ,YEAR = 1995 ,month = Jun ,volume = 27 ,number = 2 ,pages = "265--267" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {This paper introduces mediated architecture for information systems as a logical evolution of client-server architecture.} } @ARTICLE{Wiederhold92 ,AUTHOR = "Gio Wiederhold" ,TITLE = "Mediators in the Architecture of Future Information Systems" ,JOURNAL = ieeecomp ,YEAR = 1992 ,month = Mar ,volume = 25 ,number = 3 ,pages = "51--60" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {Describes mediator architecture for accessing multiple information systems and discusses the related research.} } @ARTICLE{Heiler95 ,AUTHOR = "Sandra Heiler" ,TITLE = "Semantic Interoperability" ,JOURNAL = csurvey ,YEAR = 1995 ,month = Jun ,volume = 27 ,number = 2 ,pages = "271--273" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {Discusses the issues related to semantic interoperability. The purposes are to indicate why semantic interoperability is so hard to achieve, and to suggest that repository technology can provide the beginnings of help to make it easier.} } @ARTICLE{ScioreSR94 ,AUTHOR = "Edward Sciore and Michael Siegel and Arnon Rosenthal" ,TITLE = "Using Semantic Values to Facilitate Interoperability Among Heterogeneous Information Systems" ,JOURNAL = tods ,YEAR = 1994 ,month = Jun ,volume = 19 ,number = 2 ,pages = "254--290" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {Provides a theory of "semantic values" as a unit of exchange that facilatates semantic interoperability between heterogeneous information systems.} } @ARTICLE{Krueger92 ,AUTHOR = "Charles W. Krueger" ,TITLE = "Software Reuse" ,JOURNAL = csurvey ,YEAR = 1992 ,month = Jun ,volume = 24 ,number = 2 ,pages = "131--183" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {Surveys the different approaches to software reuse and uses a taxonomy to describe and compare the approaches.} } @ARTICLE{GeneserethKetchpel94 ,AUTHOR = "Michael R. Genesereth and Steven P. Ketchpel" ,TITLE = "Software Agent" ,JOURNAL = cacm ,YEAR = 1994 ,month = Jul ,volume = 37 ,number = 7 ,entered-by = "Chen-Chuan K. Chang" ,abstract = {Discusses important issues related to agent-based software engineering, which was developed to create interaperable softwares.} } @BOOK{EngelmoreMorgan88 ,AUTHOR = "Robert Engelmore and Tony Morgan" ,TITLE = "Blackboard Systems" ,PUBLISHER = "Addison-Wesley" ,YEAR = "1988" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {A collection of papers that introduce blackboard systems, that provide a historical perspective of blackboard systems, that evaluate the contributions made by different systems, and that illustrate by example the range of blackboard applications and implementations. } } @ARTICLE{DenningDenning79 ,AUTHOR = "Dorothy E. Denning and Peter J. Denning" ,TITLE = "Data Security" ,JOURNAL = csurvey ,YEAR = "1979" ,month = Sep ,volume = 11 ,number = 3 ,pages = "227--249" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {This paper discusses four kinds of security controls: access control, flow control, inference control, and data encryption. It describes the general nature of controls of each type, the kinds of problems they can and cannot solve, and their inherent limitations and weakness.} } @PHDTHESIS{cous97a ,AUTHOR = "Steve Cousins" ,TITLE = "Reification and Affordances in a User Interface for Interacting with Heterogeneous Distributed Applications" ,SCHOOL = "Stanford University" ,YEAR = "1997" ,entered-by = "Andreas Paepcke" ,keywords = "user interface, digital library, DLITE" ,abstract = {Steve Cousin's Ph.D. thesis} } @MISC{interopBiblio ,title = "An Annotated Bibliography of Interoperability Literature" ,howpublished = "http://www-diglib.stanford.edu/diglib/pub/interopbib.html" ,links = "(title:www:http://www- diglib.stanford.edu/diglib/pub/interopbib.html)" ,address = "Stanford University" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @INPROCEEDINGS{Olle96 ,AUTHOR = "T.W. Olle" ,TITLE = "Impact of Standardization Work on the Future of Information Technology" ,BOOKTITLE = "IFIP World Conference on IT Tools" ,YEAR = 1996 ,month = sep ,editor = "Nobuyoshi Terashima and Edward Altman" ,publisher = "Chapman & Hall" ,pages = "97--105" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {This paper presents the way in which international standards for information technology are organized, and what are the driving forces behind such standards. The paper abstract on the criteria for success of IT standards and suggests shortcomings in the current approach to standardization that need to be rectified to enable complete interoperability in the future.} } @INPROCEEDINGS{KayeLittle96 ,AUTHOR = "Roland Kaye and Stephen Little" ,TITLE = "Strategies and Standards for Cultural Interoperability in Global Business Systems" ,BOOKTITLE = "Proceedings of the 29th Annual Hawaii International Conference on System Sciences" ,YEAR = 1996 ,publisher = "IEEE Computer Society Press" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {Discusses the dynamics of standardization processes for achieving interoperability and compatibility necessary for global business systems.} } @INPROCEEDINGS{HullGrefenstette96 ,AUTHOR = "David A. Hull and Gregory Grefenstette" ,TITLE = "Querying Across Languages: A Dictionary-Based Approach to Multilingual Information Retrieval" ,BOOKTITLE = sigir96 ,YEAR = 1996 ,entered-by = "Chen-Chuan K. Chang" ,abstract = {This paper presents cross-language multilingual information retrieval using translated queries and a bilingual transfer dictionary. The experiments shows that multilingual IR is feasible, although performance lags considerably behind the monolingual standard.} } @INPROCEEDINGS{SheridanBallerini96 ,AUTHOR = "Paraic Sheridan and Jean Paul Ballerini" ,TITLE = "Experiments in Multilingual Information Retrieval Using the {SPIDER} system" ,BOOKTITLE = sigir96 ,YEAR = 1996 ,address = "Zurich, Switzerland" ,pages = "58--65" ,entered-by = "Chen-Chuan K. Chang" ,abstract = {This paper introduces an approach to multilingual information retrieval based on the use of thesaurus-based query expansion techniques applied over a collection of comparable multilingual documents. It shows that the SPIDER system retrieves Italian documents in response to user queries written in German with better effectiveness than a baseline system evaluating Italian queries against Italian documents.} } @INPROCEEDINGS{saha97a ,AUTHOR = "Mehran Sahami" ,TITLE = "Applications of Machine Learning to Information Access" ,BOOKTITLE = "AAAI-97, Proceedings of the Fourteenth National Conference on Artificial Intelligence" ,YEAR = 1997 ,entered-by = "Andreas Paepcke" ,abstract = {} } @INPROCEEDINGS{cres97a ,AUTHOR = "Arturo Crespo and Hector Garcia-Molina" ,TITLE = "Awareness Services for Digital Libraries" ,BOOKTITLE = "Lecture Notes in Computer Science" ,volume = "1324" ,YEAR = "1997" ,entered-by = "Andreas Paepcke" ,keywords = "distributed indexing, data consistency" ,abstract = {~} } @INCOLLECTION{wino97 ,AUTHOR = "Terry Winograd" ,TITLE = "The Design of Interaction" ,BOOKTITLE = "Beyond Calculation, The Next 50 Years of Computing" ,PUBLISHER = "Springer-Verlag" ,YEAR = "1997" ,editor = "Peter Denning and Bob Metcalfe" ,pages = "149-162" ,entered-by = "Andreas Paepcke" ,keywords = "" ,abstract = {} } @INPROCEEDINGS{flor97 ,AUTHOR = "Daniela Florescu and Daphne Koller and Alon Levy" ,TITLE = "Awareness Services for Digital Libraries" ,BOOKTITLE = vldb97 ,YEAR = "1997" ,entered-by = "Andreas Paepcke" ,keywords = "metasearchers" ,abstract = {Deals with prioritizing queries to information sources on the web, i.e., by first querying the ones more likely to be relevant.} } @TECHREPORT{chan97a ,AUTHOR = "Edward Chang and Hector Garcia-Molina" ,TITLE = "MEDIC: A Memory & Disk Cache for Multimedia Clients" ,INSTITUTION = "Stanford University" ,YEAR = "1997" ,month = "October" ,number = "SIDL-WP-1997-0076; 1997-9" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1997-9)" ,entered-by = "Andreas Paepcke" ,keywords = "multimedia" ,abstract = {} } @ARTICLE{wood97 ,AUTHOR = "Kenneth R. Wood and Tristan Richardson and Frazer Bennett and Andy Harter and Andy Hopper" ,TITLE = "Global Teleporting with Java: Toward Ubiquitous Personalized Computing" ,JOURNAL = "IEEE Computer" ,YEAR = "1997" ,month = "February" ,pages = "53--59" ,entered-by = "Andreas Paepcke" ,keywords = "shared X, ubiquitous computing" ,abstract = {They use proxies to let you access your X sessions from anywhere. They also experimented with using Netscape/Java to maintain such long-lasting sessions} } @INPROCEEDINGS{herr97 ,AUTHOR = "Ralf G. Herrtwich and Thomas Kaeppner" ,TITLE = "Network Computers---Ubiquitous Computing or Dumb Multimedia?" ,BOOKTITLE = "Third International Symposium on Autonomous Decentralized Systems" ,YEAR = "1997" ,publisher = "IEEE Computer Society Press" ,entered-by = "Andreas Paepcke" ,keywords = "Network computers" ,abstract = {Introduces the NC spec and discusses its chances} } @MISC{nets97 ,title = "CORBA/IIOP" ,year = "1997" ,howpublished = "Netscape website: http://developer.netscape.com/one/components/corba" ,entered-by = "Andreas Paepcke" ,keywords = "netscape, corba, iiop, orb, Java" ,abstract = {Describes IIOP in Netscape One, also mentions the partners in the project} } @INPROCEEDINGS{mile81 ,AUTHOR = "John Miles Smith and Philip A. Bernstein and Umeshwar Dayal and Nathan Goodman and Terry Landers and Ken W.T. Lin and Eugene Wong" ,TITLE = "Multibase -- integrating heterogeneous distributed database systems" ,BOOKTITLE = "AFIPS National Computer Conf." ,YEAR = "1981" ,entered-by = "Andreas Paepcke" ,found-in = "Paepcke's files" ,keywords = "heterogeneous database, multibase, schema integration, global queries" ,abstract = {~} } @ARTICLE{zloo77 ,AUTHOR = "M.M. Zloof" ,TITLE = "{Q}uery-by-{E}xample: a data base language" ,JOURNAL = "IBM Systems Journal" ,YEAR = "1977" ,volume = "16" ,number = "4" ,pages = "324-343" ,entered-by = "Andreas Paepcke" ,found-in = "Paepcke's files" ,keywords = "QBE, query-by-example, queries" ,abstract = {The basic citation for QBE.} } @ARTICLE{embl89 ,AUTHOR = "D.W. Embley" ,TITLE = "{NFQL}: The Natural Forms Query Language" ,JOURNAL = "ACM Transactions on Database Systems" ,YEAR = "1989" ,month = "June" ,volume = "14" ,number = "2" ,pages = "168-211" ,entered-by = "Andreas Paepcke" ,keywords = "query forms" ,abstract = {They go beyond retrieval, to include updates and other ops} } @ARTICLE{bati86 ,AUTHOR = "C. Batini and M. Lenzerini and S. Navathe" ,TITLE = "A Comparative Analysis of Methodologies for Database Schema Integration" ,JOURNAL = "ACM Computing Surveys" ,YEAR = "1986" ,volume = "18" ,number = "4" ,entered-by = "Andreas Paepcke" ,found-in = "Same (or very similar) article as the 'Bridging Hetero Dbs' book by Navathe" ,keywords = "heterogeneous databases, federated databases, schema" ,abstract = {~} } @INPROCEEDINGS{katz98 ,AUTHOR = "Michelle Baldonado and Seth Katz and Andreas Paepcke and Chen-Chuan K. Chang and Hector Garcia-Molina and Terry Winograd" ,TITLE = "An Extensible Constructor Tool for the Rapid, Interactive Design of Query Synthesizers" ,BOOKTITLE = dl98 ,YEAR = "1998" ,note = "Accessible at http://dbpubs.stanford.edu/pub/1998-48" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1998-48)" ,entered-by = "Andreas Paepcke" ,keywords = "metadata, query construction" ,abstract = { We describe an extensible constructor tool that helps information experts (e.g., librarians) create specialized query synthesizers for heterogeneous digital-library environments. A query synthesizer provides a graphical user interface in which a digital-library patron can specify a high-level, fielded, multi-source query. Furthermore, a query synthesizer interacts with a query translator and an attribute translator to transform high-level queries into sets of source-specific queries. We discuss how the constructor can facilitate discovery of available attributes (e.g., title), collation of schemas from different sources, selection of input widgets for a synthesizer (e.g., a text box or a drop-down list widget to support input of controlled vocabulary), and other design aspects. We also describe a prototype constructor we implemented, based on the Stanford InfoBus and metadata architecture.} } @INPROCEEDINGS{cres98 ,AUTHOR = "Arturo Crespo and Hector Garcia-Molina" ,TITLE = "Archival Storage for Digital Libraries" ,BOOKTITLE = dl98 ,YEAR = "1998" ,note = "Accessible at http://dbpubs.stanford.edu/pub/1998-49" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1998-49)" ,entered-by = "Andreas Paepcke" ,keywords = "awareness, push technology, distributed storage, cellular repository" ,abstract = {We propose an architecture for Digital Library Repositories that assures long-term archival storage of digital objects. The architecture is formed by a federation of independent but collaborating sites, each managing a collection of digital objects. The architecture is based on the following key components: use of signatures as object handles, no deletions of digital objects, functional layering of services, the presence of an awareness service in all layers, and use of disposable auxiliary structures. Long-term persistence of digital objects is achieved by creating replicas at several sites. } } @INPROCEEDINGS{wein98 ,AUTHOR = "Peter C. Weinstein" ,TITLE = "Ontology-Based Metadata: Transforming the MARC Legacy" ,BOOKTITLE = dl98 ,YEAR = "1998" ,entered-by = "Michelle Baldonado" ,keywords = "metadata, ontology, bibliographic relations, catalog structure" ,abstract = {Discusses how MARC data could be transformed into a logic-based ontological model of bibliographic relations. } } @ARTICLE{paep98 ,AUTHOR = "Andreas Paepcke and Chen-Chuan K. Chang and Hector Garcia-Molina and Terry Winograd" ,TITLE = "Interoperability for Digital Libraries Worldwide" ,JOURNAL = cacm ,YEAR = "1998" ,month = "April" ,volume = "41" ,number = "4" ,note = "Accessible at http://dbpubs.stanford.edu/pub/1998-24" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1998-24)" ,entered-by = "Andreas Paepcke" ,keywords = "interoperability" ,abstract = {Discusses the history and current directions of interoperability in different parts of computing systems relevant to Digital Libraries} } @TECHREPORT{ChangGarcia98 ,AUTHOR = "Chen-Chuan K. Chang and Hector Garcia-Molina" ,TITLE = "Conjunctive Constraint Mapping for Data Translation" ,INSTITUTION = "Stanford University" ,YEAR = "1998" ,month = jan ,number = "SIDL-WP-1998-0083; 1998-47" ,note = "Accessible at http://dbpubs.stanford.edu/pub/1998-47" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1998-47)" ,entered-by = "Chen-Chuan K. Chang" } @article{Balabanovic98-umuai ,author="Marko Balabanovic" ,title="Exploring versus Exploiting when Learning User Models for Text Recommendation" ,journal="User Modeling and User-Adapted Interaction (to appear)" ,volume = 8 ,number = 1 ,year = 1998 ,links = "(title:www:http://www-diglib.stanford.edu/cgi-bin/WP/get/SIDL-WP- 1997-0067)" ,entered-by = "Andreas Paepcke" } @article{Balabanovic98-intervisions ,author = "Marko Balabanovic" ,title = "The ``Slider'' Interface" ,journal = "IBM inter{V}isions" ,volume = "11" ,month = "February" ,year = 1998} @TECHREPORT{Balabanovic98-sigir ,author = "Marko Balabanovic" ,title = "An Interface for Learning Multi-topic User Profiles from Implicit Feedback" ,INSTITUTION = "Stanford University" ,YEAR = "1998" ,number = "SIDL-WP-1998-0089" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @INPROCEEDINGS{chan98 ,AUTHOR = "Edward Chang and Hector Garcia-Molina" ,TITLE = "Cost-Based Media Server Design" ,BOOKTITLE = "To appear in the proceedings of the 8th Research Issues in Data Engineering" ,YEAR = "1998" ,month = "Feb" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1998-42)" ,entered-by = "Andreas Paepcke" ,abstract = {~} } @INPROCEEDINGS{chan98a ,AUTHOR = "Edward Chang" ,TITLE = "An Image Coding and Reconstruction Scheme for Mobile Computing" ,BOOKTITLE = "Proceedings of the 5th IDMS (Springer-Verlag LNCS 1483), p.137- 148, Oslo, Norway, September 1998." ,YEAR = "1998" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1997-10)" ,note = "Accessible at http://dbpubs.stanford.edu/pub/1997-10" ,entered-by = "Andreas Paepcke" ,abstract = {An asynchronous transfer mode (ATM) wireless network has bursty and high error rates. To combat the contiguous bit loss due to damaged or dropped packets, this paper presents a code packetization and image reconstruction scheme. The packetization method distributes the loss in both frequency and spatial domains to reduce the chance that adjacent DCT blocks lose the same frequency components. The image reconstruction takes into consideration the spatial characteristics represented by the frequency components. Combining these two approaches is able to reconstruct the damaged images more accurately, even under very high loss rates. In addition, since the reconstruction technique is computational efficient, it conserves system resources and power consumption, which are restrictive in mobile computers.} } @TECHREPORT{brin98c ,AUTHOR = "Sergey Brin and Lawrence Page" ,TITLE = "Dynamic Data Mining: A New Architecture for Data with High Dimensionality" ,INSTITUTION = "Stanford University" ,YEAR = "1998" ,entered-by = "Andreas Paepcke" ,keywords = "google" ,abstract = {Describes a new architecture for data mining. It makes use of some of the dynamic itemset counting technology} } @INPROCEEDINGS{brin98a ,AUTHOR = "Sergey Brin and Lawrence Page" ,TITLE = "The Anatomy of a Large-Scale Hypertextual Web Search Engine" ,BOOKTITLE = www98 ,YEAR = "1998" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1998-8)" ,entered-by = "Andreas Paepcke" ,keywords = "Google" ,abstract = {Shows architecture of Google.} } @TECHREPORT{page98 ,AUTHOR = "Lawrence Page and Sergey Brin and Rajeev Motwani and Terry Winograd" ,TITLE = "The PageRank Citation Ranking: Bringing Order to the Web" ,YEAR = "1998" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1999-66)" ,institution = "Computer Science Department, Stanford University" ,entered-by = "Andreas Paepcke" ,keywords = "Google, Backrub, page rank" } @TECHREPORT{nara98 ,AUTHOR = "Shiva Narayanan and Hector Garcia-Molina" ,TITLE = "Computing iceberg queries efficiently" ,INSTITUTION = "Stanford University" ,YEAR = "1998" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1999-67)" ,entered-by = "Andreas Paepcke" ,abstract = {Iceberg queries are queries about the 'most' of or 'biggest' of a set.} } @INPROCEEDINGS{cho98 ,AUTHOR = "Junghoo Cho and Hector Garcia-Molina and Lawrence Page" ,TITLE = "Efficient Crawling Through URL Ordering" ,BOOKTITLE = www98 ,YEAR = "1998" ,note = "Available at http://dbpubs.stanford.edu/pub/1998-51" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1998-51)" ,entered-by = "Andreas Paepcke" ,keywords = "crawling" ,abstract = {In this paper we study in what order a crawler should visit the URLs it has seen, in order to obtain more "important" pages first. Obtaining important pages rapidly can be very useful when a crawler cannot visit the entire Web in a reasonable amount of time. We define several importance metrics, ordering schemes, and performance evaluation measures for this problem. We also experimentally evaluate the ordering schemes on the Stanford University Web. Our results show that a crawler with a good ordering scheme can obtain important pages significantly faster than one without.} } @INPROCEEDINGS{jame97 ,AUTHOR = "Frankie James" ,TITLE = "Distinguishability vs. Distraction in Audio HTML Interfaces" ,BOOKTITLE = "Submitted to International Journal on Digital Libraries" ,YEAR = "1997" ,entered-by = "Andreas Paepcke" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1997-82)" ,keywords = "audio browser, AHA" ,abstract = {Analyzes results from a user study related to the AHA (Audio HTML Access) framework, which tested three audio browsers to determine the appropriateness of certain types of audio markings for various HTML structures. The results added another dimension to the AHA framework, so that the principles outlined in it for choosing sounds to use in an audio presentation of HTML are now: (1) Vocal Source Identity (when to use speaker changes to mark structures), (2) Recognizability, and (3) Distraction (new)} } @ARTICLE{jame97a ,AUTHOR = "Frankie James" ,TITLE = "Lessons from Developing Audio HTML Interfaces" ,JOURNAL = "ACM SIGCAPH Conference on Assistive Technologies Proceedings of the third international ACM conference on Assistive technologies. April 15-17, 1998, Marina del Rey, CA USA, pages 27-34." ,YEAR = "1998" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-45)" ,entered-by = "Andreas Paepcke" ,keywords = "AHA, audio browser" ,abstract = {Discusses application of the principles in the AHA framework to the actual choice of sounds in scenario interfaces. By looking at scenarios, we can see that other factors related to users (such as musical ability, culture, reading style, etc.) are needed in combination with the AHA principles to select specific sounds.} } @inproceedings{saha98 ,author={Mehran Sahami and Salim Yusufali and Michelle Baldonado} ,title={SONIA: A Service for Organizing Networked Information Autonomously} ,booktitle = dl98 ,year = "1998" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-48)" } @TECHREPORT{gold98a ,author={Moises Goldszmidt and Mehran Sahami} ,title={A Probabilistic Approach to Full-Text Document Clustering} ,INSTITUTION = "SRI International" ,YEAR = "1998" ,entered-by = "Andreas Paepcke" } @MISC{CyberWeb ,author = "CyberCash" ,title = "CyberCash Home Page" ,howpublished = "CyberCash website: http://www.cybercash.com/" ,entered-by = "Neil Daswani" ,keywords = "CyberCash, SET, credit card, online payment, CyberCoin, electronic check" } @MISC{DigiWeb ,author = "DigiCash" ,title = "DigiCash: Solutions for Security and Privacy" ,howpublished = "DigiCash website: http://www.digicash.com/" ,entered-by = "Neil Daswani" ,keywords = "DigiCash, payment, digital cash, ecash, online payment" } @MISC{Milcnt ,author = "Digital Equipment Corporation" ,title = "MilliCent" ,howpublished = "MilliCent website: http://www.millicent.digital.com/" ,entered-by = "Neil Daswani" ,keywords = "micropayment, microtransactions, online payment" } @MISC{MSW ,author = "Microsoft Corporation" ,title = "Microsoft Wallet" ,howpublished = "Microsoft wallet website: http://www.microsoft.com/wallet/" ,entered-by = "Neil Daswani" ,keywords = "digital wallet, online payment, SET, credit card" } @MISC{JECFWeb ,author = "Sun Microsystems" ,title = "Java Commerce Home Page" ,howpublished = "JavaSoft website: http://java.sun.com/commerce/" ,entered-by = "Neil Daswani" ,keywords = "digital wallet, JECF, Java, SET" } @MISC{SET ,author = "Visa and Mastercard" ,title = "Mastercard International - SET Secure Electronic Transaction (TM)" ,howpublished = "Mastercard website: http://www.mastercard.com/set/" ,entered-by = "Neil Daswani" ,keywords = "SET, credit card, online payment, Mastercard" } @INPROCEEDINGS{DH66 ,AUTHOR = "Jack B. Dennis and Earl C. Van Horn" ,TITLE = "Programming Semantics for Multiprogrammed Computations" ,BOOKTITLE = cacm ,YEAR = "1966" ,entered-by = "Neil Daswani" } @INPROCEEDINGS{GEPS96 ,AUTHOR = "Alireza Behreman" ,TITLE = "Generic Electronic Payment Services" ,BOOKTITLE = "The Second USENIX Workshop on Electronic Commerce Proceedings" ,YEAR = "1996" ,entered-by = "Neil Daswani" } @INPROCEEDINGS{PMNS96 ,AUTHOR = "Alireza Behreman and Rajkumar Narayanaswamy" ,TITLE = "Payment Method Negotiation Service" ,BOOKTITLE = "The Second USENIX Workshop on Electronic Commerce Proceedings" ,YEAR = "1996" ,entered-by = "Neil Daswani" } @MISC{upp ,author = "D. Eastlake" ,title = "Universal Payment Preamble Specification" ,howpublished = "W3C website: http://www.w3.org/ECommerce/specs/upp.txt" ,entered-by = "Neil Daswani" ,keywords = "payment protocol negotiation, UPP, online payment, JEPI" } @MISC{jcmwp ,title = "Java Commerce Messages White Paper" ,howpublished = "Sun Microsystems website: http://java.sun.com/products/commerce/docs/whitepapers/jcm_whitepaper/jcm_whitep aper.html" ,entered-by = "Neil Daswani" ,keywords = "JECF, Java, electronic commerce" } @MISC{JEPIWeb ,title = "W3C Joint Electronic Payments Initiative (JEPI)" ,howpublished = "W3C website: http://www.w3.org/ECommerce/Overview-JEPI.html" ,entered-by = "Neil Daswani" ,keywords = "electronic commerce, W3C, JEPI, UPP" } @INPROCEEDINGS{cts95 ,AUTHOR = "B. Cox and D. Tygar and M. Sirbu" ,TITLE = "NetBill Security and Transaction Protocol" ,BOOKTITLE = "First USENIX Workshop of Electronic Commerce Proceedings" ,YEAR = "1995" ,entered-by = "Neil Daswani" ,keywords = "security, atomicity, transaction, electronic commerce, delivery, online payment" } @MISC{FVWeb ,title = "First Virtual Home Page" ,howpublished = "First Virtual website: http://www.fv.com/" ,entered-by = "Neil Daswani" ,keywords = "online payment, electronic commerce, VirtualPIN" } @INPROCEEDINGS{mn94 ,AUTHOR = "G. Medvinsky and C. Neuman" ,TITLE = "NetCash: A Design for Practical Electronic Currency on the Internet" ,BOOKTITLE = "Proceedings of the Second ACM Conference on Computer and Communication Security" ,YEAR = "1994" ,entered-by = "Neil Daswani" ,keywords = "digital cash, electronic commerce, payment" } @INPROCEEDINGS{ams96 ,AUTHOR = "R. Anderson and C. Manifavas and C. Sutherland" ,TITLE = "Netcard - A Practical Electronic Cash System" ,BOOKTITLE = "Fourth Cambridge Workshop on Security Protocols" ,YEAR = "1996" ,entered-by = "Neil Daswani" ,keywords = "electronic cash, digital cash" } @INPROCEEDINGS{dasw98 ,AUTHOR = "Neil Daswani and Dan Boneh and Hector Garcia-Molina and Steven Ketchpel and Andreas Paepcke" ,TITLE = "A Generalized Digital Wallet Architecture" ,BOOKTITLE = "Proceedings of the 3rd USENIX Workshop on Electronic Commerce, p. 121-39 " ,YEAR = "1998" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-49)" ,entered-by = "Andreas Paepcke" ,keywords = "digital wallets, ecommerce, upai, shopping models" ,abstract = {Publishers wishing to distribute text online fear that customers will download their product and redistribute it illegally. Although constraining the users to access the data only through proprietary software that does not allow downloading helps, it still leaves the possibility that users could take screen dumps of the material to capture it. The technique described in the paper relies on the perceptual properties of the human eye, using two unreadable images interleaved quickly to create a readable image, which cannot be screen-dumped since the readability depends on averaging in the human eye. Our program flickers two images of the text each with an admixture of grey noise. Your eye sorts out the letters and reads them, not paying close attention to the grey background; but any screen dump captures the item at one instant including the noise. The text is also scrolled up and down slowly, which again your eye can track, but which would frustrate a program trying to average out the flickering.} } @INPROCEEDINGS{bgh95 ,AUTHOR = "M. Bellare and J.A. Garay and R. Hauser and A. Herzberg and H. Krawczyk and M. Steiner and G. Tsudik and M. Waidner" ,TITLE = "iKP-a family of secure electronic payment protocols" ,BOOKTITLE = "Proceedings of the First USENIX Workshop of Electronic Commerce" ,YEAR = "1995" ,publisher = "USENIX Assoc" ,address = "Berkeley, CA, USA" ,entered-by = "Neil Daswani" ,keywords = "cryptography, EFTS, Internet, protocols iKP, secure electronic payment protocols, Internet, credit card-based transactions, financial network, clearing, authorization, debit cards, electronic checks, public-key cryptography, key management complexity" ,abstract = {This paper proposes a family of protocols-iKP (i=1,2,3)-for secure electronic payments over the Internet. The protocols implement credit card-based transactions between the customer and the merchant while using the existing financial network for clearing and authorization. The protocols can be extended to apply to other payment models, such as debit cards and electronic checks. They are based on public-key cryptography and can be implemented in either software or hardware. Individual protocols differ in key management complexity and degree of security. It is intended that their deployment be gradual and incremental. The iKP protocols are presented herein with the intention to serve as a starting point for eventual standards on secure electronic payment.} } @INPROCEEDINGS{ak96 ,AUTHOR = "R. Anderson and M. Kuhn" ,TITLE = "Tamper resistance--a cautionary note" ,BOOKTITLE = "Proceedings of the Second USENIX Workshop on Electronic Commerce" ,YEAR = "1996" ,publisher = "USENIX Assoc" ,address = "Berkeley, CA, USA" ,entered-by = "Neil Daswani" ,keywords = "cryptography, security of data, smart cards, pay-TV, electronic purses, tamper resistance, smartcards, security processors, chip testing community, secure systems" ,abstract = {"An increasing number of systems, from pay-TV to electronic purses, rely on the tamper resistance of smartcards and other security processors. We describe a number of attacks on such systems some old, some new and some that are simply little known outside the chip testing community. We conclude that trusting tamper resistance is problematic; smartcards are broken routinely, and even a device that was described by a government signals agency as the most secure processor generally available' turns out to be vulnerable. Designers of secure systems should consider the consequences with care."} } @INPROCEEDINGS{Manasse95 ,AUTHOR = "M.S. Manasse" ,TITLE = "The Millicent protocols for electronic commerce" ,BOOKTITLE = "Proceedings of the First USENIX Workshop of Electronic Commerce" ,YEAR = "1995" ,publisher = "USENIX Assoc" ,address = "Berkeley, CA, USA" ,entered-by = "Neil Daswani" ,keywords = "access protocols, client-server systems, cryptography, distributed databases, EFTS, information retrieval, memory protocols, transaction processing, Millicent protocols, electronic commerce, cryptography, untrusted intermediary, self-messaging, storage costs, infrequently accessed information, client-server system, prefetch unit, memory states, seek time, database,information verification, transaction aggregation service, transaction granularity scale, incomplete information, fund transfer, information retrieval, cheating, limited transaction scale, consumer risk level control " ,abstract = {"Cryptography can be useful to send yourself a message via an untrusted intermediary. Pushing the cost of storing infrequently accessed information off to the client allows the servers to run quickly: the network acts as a perfect prefetch unit for loading your memory with the necessary state for the next operation. By way of example, a server that has to store a lot of information about subscribers might buckle under the seek time of accessing subscriber records. Pushing it off to clients allows us to have the salient parts of the database arrive in memory precisely when needed, at the small cost of verifying that the information hasnt been tampered with. A service can help aggregate the transactions into a grain large enough to be acceptable to more conventional transaction handlers, without providing complete information about the transaction to the service. By making fund transfer explicit in each retrieval, all parties involved can instantly tell when theyre being cheated; by limiting the scale of transaction, consumers can control the level of risk they accept."} } @INPROCEEDINGS{sw97 ,AUTHOR = "M. Schunter and M. Waidner" ,TITLE = "Architecture and design of a secure electronic marketplace" ,BOOKTITLE = "Proceedings of JENC8. 8th Joint European Networking Conference (JENC8). Diversity and Integration: The New European Networking Landscape" ,YEAR = "1997" ,editor = "Lubich, H." ,publisher = "TERENA" ,address = "Amsterdam, Netherlands" ,entered-by = "Neil Daswani" ,keywords = "business data processing, Internet, retailing, security of data, secure electronic marketplace, secure commerce, Internet, public information networks, SEMPER, business scenario, commerce layer, exchange and transfer layer, Java programming language, multimedia courseware, mail-order retailing, payment systems, ecash" ,abstract = {"Backed by the European Commission, a consortium of partners from European industry, financial institutions, and academia has embarked on a research project to develop the fundamentals of secure electronic commerce. The goal of the ACTS Project SEMPER (Secure Electronic Marketplace for Europe) is to provide the first open and comprehensive solution for secure commerce over the Internet and other public information networks. SEMPER's flexible open architecture is based on a model of electronic commerce which comprehends a business scenario as a sequence of transfers and fair exchanges of "business items", which are payments, data, or rights. This is reflected in the architecture: The exchange and transfer layer handles transfers and fair exchanges of items. The commerce layer provides methods for downloading certified commerce services and the necessary trust management. The commerce services implement the terms of business of a seller using the exchange and transfer layer services. A prototype of this architecture implemented in the Java programming language will be trialed for sales of multimedia courseware (EUROCOM, Athens, GR), on-line consultancy and subscriptions (FOGRA, Munchen, D) as well as mail-order retailing (Otto-Versand, Hamburg, D). It will integrate the payment systems SET (provided by IBM), Chipper (provided by KPN Research), and ecash (provided by DigiCash). The prototype uses a distinguished user-interface for trustworthy user in- and output which enables to use SEMPER on secure hardware." } } @INPROCEEDINGS{www98 ,AUTHOR = "Peter R. Wurman and Mechael P. Wellman and William E. Walsh" ,TITLE = "The Michigan Internet AuctionBot: A Configurable Auction Server for Human and Software Agents" ,BOOKTITLE = "Proceedings of the Second International Conference on Autonomous Agents (Agents-98)" ,YEAR = "1998" ,entered-by = "Neil Daswani" ,keywords = "Internet, auction, electronic commerce, autonomous agents" } @TECHREPORT{aas98 ,AUTHOR = "J.L. Abad Peiroa and N. Asokan and M. Steiner and M. Waidner" ,TITLE = "IBM Systems Journal" ,INSTITUTION = "IBM" ,YEAR = "1998" ,month = "" ,number = "37" ,entered-by = "Neil Daswani" ,keywords = "application program interfaces, commerce, financial data processing, generic payment service, electronic commerce, incompatible payment systems, business application developers, payment instrument, common framework, application programming interfaces, transparent negotiation, payment information" ,abstract = {"The growing importance of electronic commerce has resulted in the introduction of a variety of different and incompatible payment systems. For business application developers, this variety implies the need to understand the details of different systems, to adapt the code as soon as new payment systems are introduced and also to provide a way of picking a suitable payment instrument for every transaction. We unify the different mechanisms in a common framework with application programming interfaces. Our framework provides services for transparent negotiation and selection of payment instruments as well. This allows applications to be developed independent of specific payment systems with the additional benefit of providing a central point of control for payment information and policies."} } @ARTICLE{ajs97 ,AUTHOR = "N. Asokan and P.A. Janson and M. Steiner and M. Waidner" ,TITLE = "The state of the art in electronic payment systems" ,JOURNAL = "Computer" ,YEAR = "1997" ,month = "September" ,volume = "30" ,number = "9" ,pages = "28-35" ,entered-by = "Neil Daswani" ,keywords = "EFTS; reviews; security of data; electronic payment systems; exchange of goods; security problems; risks; digital documents; perfect copies; digital signatures; cryptographic key; buyer's name; security measures; electronic commerce; flexibility; overview" ,abstract = {"The exchange of goods conducted face-to-face between two parties dates back to before the beginning of recorded history. Traditional means of payment have always had security problems, but now electronic payments retain the same drawbacks and add some risks. Unlike paper, digital "documents" can be copied perfectly and arbitrarily often, digital signatures can be produced by anybody who knows the secret cryptographic key, and a buyer's name can be associated with every payment, eliminating the anonymity of cash. Without new security measures, widespread electronic commerce is not viable. On the other hand, properly designed electronic payment systems can actually provide better security than traditional means of payments, in addition to flexibility. This article provides an overview of electronic payment systems, focusing on issues related to security."} } @INPROCEEDINGS{gkd97 ,AUTHOR = "M.R. Genesereth and A.M. Keller and O.M. Duschka" ,TITLE = "Infomaster: an information integration system" ,BOOKTITLE = "SIGMOD Record" ,YEAR = "1997" ,publisher = "ACM Press" ,address = "New York" ,entered-by = "Neil Daswani" ,keywords = "distributed databases, hypermedia, Internet, online front-ends, information integration system, Infomaster, multiple distributed heterogeneous information sources, Internet, centralized homogeneous information system, virtual data warehouse, content translation, multiple data sources, wrappers, SQL databases, World Wide Web, WWW user interfaces, programmatic interface, meeting room scheduling" ,abstract = {"Infomaster is an information integration system that provides integrated access to multiple distributed heterogeneous information sources on the Internet, thus giving the illusion of a centralized, homogeneous information system. We say that Infomaster creates a virtual data warehouse. The core of Infomaster is a facilitator that dynamically determines an efficient way to answer the user's query using as few sources as necessary and harmonizes the heterogeneities among these sources. Infomaster handles both structural and content translation to resolve differences between multiple data sources and the multiple applications for the collected data. Infomaster connects to a variety of databases using wrappers, such as for Z39.50, SQL databases through ODBC, EDI transactions, and other World Wide Web (WWW) sources. There are several WWW user interfaces to Infomaster, including forms based and textual. Infomaster also includes a programmatic interface and it can download results in structured form onto a client computer. Infomaster has been in production use for integrating rental housing advertisements from several newspapers (since fall 1995), and for meeting room scheduling (since winter 1996). Infomaster is also being used to integrate heterogeneous electronic product catalogs."} } @INPROCEEDINGS{goldstein97 ,AUTHOR = "T. Goldstein" ,TITLE = "The Gateway security model in the Java electronic commerce framework" ,BOOKTITLE = "Financial Cryptography First International Conference, FC'97. Proceedings." ,YEAR = "1997" ,editor = "Hirschfeld, R." ,publisher = "Springer-Verlag" ,address = "Berlin, Germany" ,entered-by = "Neil Daswani" ,keywords = "financial data processing, message authentication, electronic commerce, Java electronic commerce framework, Java security model, Gateway security model,digital signatures, application programming interfaces, integrated open platform, electronic wallets, point of sale terminals, electronic merchant servers, financial software, access control, multiple application environments, trusted interaction, browsers, servers, operating systems, medical systems, smartcards" ,abstract = {"This paper describes an extension to the current Java security model called the "Gateway" and why it was necessary to create it. This model allows secure applications, such as those used in electronic commerce, to safely exchange data and interoperate without compromising each individual application's security. The Gateway uses digital signatures to enable application programming interfaces to authenticate their caller. JavaSoft is using the Gateway to create a new integrated open platform for financial applications called Java Electronic Commerce Framework. The JECF will be the foundation for electronic wallets, point of sale terminals, electronic merchant servers and other financial software. The Gateway model can also be used for access control in many multiple application environments that require trusted interaction between applications from multiple vendors. These applications include browsers, servers, operating systems, medical systems and smartcards."} } @ARTICLE{aya96 ,AUTHOR = "N. Adam and Y. Yesha and B. Awerbuch and K. Bennet and B. Blaustein and A. Brodsky and R. Chen and O. Dogramaci and B. Grossman and R. Holowczak and J. Johnson K. Kalpakis and C. McCollum and A.-L. Neches and B. Neches and A. Rosenthal and J. Slonim and H. Wactlar and O. Wolfson" ,TITLE = "Strategic directions in electronic commerce and digital libraries: towards a digital Agora" ,JOURNAL = "ACM Computing Surveys" ,YEAR = "1996" ,month = "December" ,volume = "28" ,number = "4" ,pages = "818-35" ,entered-by = "Neil Daswani" ,keywords = "business data processing, costing, EFTS, information retrieval, library automation, research initiatives, socio-economic effects, strategic directions, electronic commerce, digital libraries, research requirements, case studies, research projects, USC-ISI, CommerceNet, First Virtual, NSF ARPA NASA initiative, information storage, information filtering, auditing, security, universal access, cost management, financial instruments, socio-economic impact, EFTS" ,abstract = {"The paper examines the research requirements of electronic commerce and digital libraries in six key areas. It provides case studies that describe three electronic commerce research projects (USC-ISI, CommerceNet, First Virtual) and six digital libraries projects sponsored by an NSF/ARPA/NASA initiative. The paper focuses on the following common areas of EC and DL research: acquiring and storing information; finding and filtering information; securing information and auditing access; universal access; cost management and financial instruments; and socio-economic impact."} } @InProceedings{alan97, author = "T. Alanko and M. Kojo and M. Liljeberg and K. Raatikainen", title = "Mowgli: improvements for Internet applications using slow wireless links", volume = 3, pages = "1038-42", booktitle = "Waves of the Year 2000+ PIMRC '97. The 8th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications. Technical Program, Proceedings (Cat. No.97TH8271)", year = 1997, entered-by = "Henry Berg", abstract = "Modern cellular telephone systems extend the usability of portable personal computers enormously. A nomadic user can be given ubiquitous access to remote information stores and computing services. However, the behavior of wireless links creates severe inconveniences within the traditional data communication paradigm. We give an overview of the problems related to wireless mobility. We also present a new software architecture for mastering the problems and discuss a new paradigm for designing mobile distributed applications. The key idea in the architecture is to place a mediator, a distributed intelligent agent, between the mobile node and the wireline network." } @Article{badr96, author = "B. R. Badrinath", title = "Distributed computing in mobile environments", journal = "Computers & Graphics", year = 1996, volume = 20, number = 5, pages = "615-17", entered-by = "Henry Berg", abstract = "Rapid progress in hardware has led to the availability of portable personal computers ranging from laptops to hand-held computers (PDAs and Internet terminals). The presence of wireless connectivity gives these hand-held units the capability of accessing information anywhere, at any time. These mobile units can be considered to be part of a worldwide distributed information system. Distributed computing in mobile environments faces new challenges as more and more mobile hosts become an integral part of a distributed system. Problems in distributed computing in mobile environments are due to: (1) mobility, (2) wireless and (3) resource constraints at the mobile host. In this paper, we discuss the impact of these factors and research issues that need to be addressed in mobile distributed systems." } @Article{beig96, author = "M. Beigl and R. Rudisch", title = "System support for mobile computing", journal = "Computers & Graphics", year = 1996, volume = 20, number = 5, pages = "619-625", entered-by = "Henry Berg", abstract = "Today a mobile user wants to connect his portable computer: remotely to the central database at home, locally to the printer on the spot and globally to the world-wide-web. To achieve this, different connection lines are available: wireless networks for connecting out in the fields, ISDN or analogue telephone lines when residing in a hotel, Ethernet access at the customer's site. But this connectivity raises a lot of questions, about technical, security or accounting issues. This paper presents the architecture of an environment aiming to support mobile users and dealing with the given problems." } @Article{li97, author = "Yalun Li and V. Leung", title = "Supporting personal mobility for nomadic computing over the internet", journal = "Mobile computing and communications review", year = 1997, volume = 1, number = 1, pages = "22-31", entered-by = "Henry Berg", abstract = "This paper presents a new paradigm for nomadic computing over the internet called universal personal computing (UPC), where mobile users can access computing resources, network services, and personalized computing environments anywhere using any available terminals. The concept of UPC and system design issues are discussed, and the required system architecture capable of managing different mobile objects, i.e. users and terminals, in the UPC environment is presented. Modifications of connection setup procedures between user application programs to enable addressing based on a global user identity are considered." } @Article{miah97, author = "T. Miah and O. Bashir", title = "Mobile workers: access to information on the move", key = "mobile computing; information access; pen computing; personal digital assistants; client server systems; mobile computing architecture; network topologies; hospital ward; PDA; patient records", journal = "Computing & Control Engineering Journal", year = 1997, volume = 8, number = 5, pages = "215-23", month = "Oct", entered-by = "Henry Berg", abstract = "As the development of pen computing' continues, more and more of today's computers are likely gradually to move away from people's desktops and into their pockets. The development of personal digital assistants (PDAs) has initiated this move. As these devices move into people's pockets, they need the ability to access information on the move. This article describes a generic view of a client server mobile computing architecture. It also sheds some light on the basic network topologies that have been considered previously for such systems. The scenario used is a hospital ward. Each doctor is equipped with a PDA and each ward or a group of wards with a server providing patient records. As a doctor visits a patient in a ward, the patient's record is accessed from the server onto the PDA. The doctor updates the record and sends the update back to the server." } @Article{boni96, author = "J. Bonigk and A. Lubinski", title = "A basic architecture for mobile information access", key = "basic architecture; mobile information access; globally distributed information; information exchange; mobile computing environment; Object Bus; message handler processes; type dependent message handling; object manager; dynamically changing resources; mobile environment; communication channels; user preferences", journal = "Computers & Graphics", year = 1996, volume = 20, number = 5, pages = "683-91", entered-by = "Henry Berg", abstract = "As the development of pen computing' continues, more and more of today's computers are likely gradually to move away from people's desktops and into their pockets. The development of personal digital assistants (PDAs) has initiated this move. As these devices move into people's pockets, they need the ability to access information on the move. This article describes a generic view of a client server mobile computing architecture. It also sheds some light on the basic network topologies that have been considered previously for such systems. The scenario used is a hospital ward. Each doctor is equipped with a PDA and each ward or a group of wards with a server providing patient records. As a doctor visits a patient in a ward, the patient's record is accessed from the server onto the PDA. The doctor updates the record and sends the update back to the server." } @Article{kirs96, author = "T. Kirste and U. Rauschenbach", title = "A presentation model for mobile information visualization", key = "presentation model; mobile information visualization; information environment; homogeneous access; mobile computing infrastructure; distributed information system; user requirements; display functionality; alternative display methods; recursive view generation process; influence parameters; user characteristics; display resources; data properties; user goals", journal = "Computers & Graphics", year = 1996, volume = 20, number = 5, pages = "669-81", entered-by = "Henry Berg", abstract = {One of the visions of mobile computing is to put "all information at the user's fingertips"-to allow a user to operate on any data, any time, anywhere. The idea is to create an information environment providing homogeneous access to all data and services available in the distributed, mobile computing infrastructure. A fundamental requirement for access to such an open, distributed information system is an intelligent selection of methods for information visualization based on user requirements and available display functionality. A flexible concept is proposed that allows one to enrich the nodes of an information structure with information about which alternative display methods can be used for what parts of the node. These facets' are then used by a recursive view generation process for selecting suitable display methods while creating a visualization of an information structure. Influence parameters such as user characteristics, display resources, and data properties can be used to guide the selection process in order to create a presentation that optimally meets the user's goals.} } @Article{dunh97, author = "M. H. Dunham and A. Helal", title = "A mobile transaction model that captures both the data and movement behavior", key = "mobile transaction model; split transactions; global transactions; multidatabase environment; kangaroo transactions; split operations; concurrency control; recovery solutions", journal = "Mobile Networks and Applications", year = 1997, volume = 2, number = 2, pages = "149-62", entered-by = "Henry Berg", abstract = "Unlike distributed transactions, mobile transactions do not originate and end at the same site. The implication of the movement of such transactions is that classical atomicity, concurrency and recovery solutions must be revisited to capture the movement behavior. As an effort in this direction, we define a model of mobile transactions by building on the concepts of split transactions and global transactions in a multidatabase environment. Our view of mobile transactions, called kangaroo transactions, incorporates the property that transactions in a mobile computing system hop from one base station to another as the mobile unit moves through cells. Our model is the first to capture this movement behavior as well as the data behavior which reflects the access to data located in databases throughout the static network. The mobile behavior is dynamic and is realized in our model via the use of split operations. The data access behavior is captured by using the idea of global and local transactions in a multidatabase system." } @Article{yen97, author = "Li-Hsing Yen and Ting-Lu Huang and Shu-Yuen Hwang", title = "A protocol for causally ordered message delivery in mobile computing systems", journal = "Mobile Networks and Applications", year = 1997, volume = 2, number = 2, pages = "365-72", entered-by = "Henry Berg", abstract = "There is a growing trend in developing applications for mobile computing systems in which mobile host computers retain their network connections while in transit. This paper proposes an algorithm that enforces a useful property, namely, causal ordering, that delivers messages among mobile hosts. This property ensures that causally related messages directed to the same destination will be delivered in an order consistent with their causality, which is important in applications that involve human interaction such as mobile e-mail and mobile teleconferencing. Such applications are envisioned by the proponents of Personal Communications Services (PCS). Without this property, users may receive and read original messages and the corresponding replies out of order. Our algorithm, when compared with previous proposals, provides an alternative with a low handoff cost, medium message overhead, and low probability of unnecessary inhibition in delivering messages." } @Article{kell97, author = "A. Keller and O. Densmore and Wei Huang and B. Razavi", title = "Zippering: Managing Intermittent Connectivity in DIANA", journal = "Mobile Networks and Applications", year = 1997, volume = 2, number = 2, pages = "357-64", entered-by = "Henry Berg", abstract = "This paper describes an approach for handling intermittent connectivity between mobile clients and network-resident applications, which we call zippering. When the client connects with the application, communication between the client and the application is synchronous. When the client intermittently connects with the application, communication becomes asynchronous. The DIANA (Device-Independent, Asynchronous Network Access) approach allows the client to perform a variety of operations while disconnected. Finally, when the client reconnects with the application, the operations performed independently on the client are replayed to the application in the order they were originally done. Zippering allows the user at the client to fix errors detected during reconciliation and continues the transaction gracefully instead of aborting the whole transaction when errors are detected." } @InProceedings{lee96, author = "Wang-Chien Lee and Dik Lun Lee", title = "Information filtering in wireless and mobile environments", key = "mobile environments; wireless environments; power conservation; mobile clients; palmtop computers; signature methods; real-time information filtering; wireless communication services; signature-based approaches; simple signature; multilevel signature; cost models; access time; tune-in time; wireless data networks; packet radio", pages = "508-14", booktitle = "Conference Proceedings of the 1996 IEEE Fifteenth Annual International Phoenix Conference on Computers and Communications (Cat. No.96CH35917)", year = 1996, entered-by = "Henry Berg", abstract = "The paper describes the issue of power conservation on mobile clients, e.g., palmtop computers, and suggests that signature methods are suitable for real-time information filtering on wireless communication services. Two signature-based approaches, namely simple signature and multi-level signature schemes, are presented. Cost models for access time and tune-in time of these two approaches are developed." } @InProceedings{weis94, author = "M. Weiser and B. Welch and A. Demers and S. Shenker", title = "Scheduling for reduced CPU energy", key = "reduced CPU energy; energy usage; scheduling; battery operated systems; displays; disks; metric; CPU energy performance; dynamic control; system clock speed; operating system scheduler; adiabatic logic; reversible logic; clock-speed; Unix; workstation traces; CPU energy; performance", pages = "13-23", booktitle = "Proceedings of the First USENIX Symposium on Operating Systems Design and Implementation (OSDI)", year = 1994, entered-by = "Henry Berg", abstract = " The energy usage of computer systems is becoming more important, especially for battery operated systems. Displays, disks, and CPUs, in that order, use the most energy. Reducing the energy used by displays and disks has been studied elsewhere; this paper considers a new method for reducing the energy used by the CPU. We introduce a new metric for CPU energy performance, millions-of-instructions-per-joule (MIPJ). We examine a class of methods to reduce MIPJ that are characterized by dynamic control of system clock speed by the operating system scheduler. Reducing clock speed alone does not reduce MIPJ, since to do the same work the system must run longer. However, a number of methods are available for reducing energy with reduced clock-speed, such as reducing the voltage (Chandrakasan et al., 1992) (Horowitz, 1993) or using reversible (Younis and Knight, 1993) or adiabatic logic (Athas et al., 1994). What are the right scheduling algorithms for taking advantage of reduced clock-speed, especially in the presence of applications demanding ever more instructions-per-second? We consider several methods for varying the clock speed dynamically under control of the operating system, and examine the performance of these methods against workstation traces. The primary result is that by adjusting the clock speed at a fine grain, substantial CPU energy can be saved with a limited impact on performance." } @Article{stem97, author = "M. Stemm and R. H. Katz", title = "Measuring and reducing energy consumption of network interfaces in hand-held devices", key = "modems; network interfaces; notebook computers; optimisation; power consumption; power measurement; wireless LAN; energy consumption; network interfaces; hand-held devices; PDA; Apple Newton Messagepad; Sony Magic Link; Metricom Ricochet Wireless Modem; AT&T Wavelan; IBM Infrared Wireless LAN Adapter; optimizations; transport-level strategies; application-level strategies; 915 MHz; 2.4 GHz", journal = "IEICE Transactions on Communications, vol.E80-B, no.8, p. 1125-31", year = 1997, volume = "E80-B", number = 8, pages = "1125-31", entered-by = "Henry Berg", abstract = "Next generation hand-held devices must provide seamless connectivity while obeying stringent power and size constraints. We examine this issue from the point of view of the network interface (NI). We measure the power usage of two PDAs, the Apple Newton Messagepad and Sony Magic Link, and four NIs, the Metricom Ricochet Wireless Modem, the AT&T Wavelan operating at 915 MHz and 2.4 GHz, and the IBM Infrared Wireless LAN Adapter. These measurements clearly indicate that the power drained by the network interface constitutes a large fraction of the total power used by the PDA. We then examine two classes of optimizations that can be used to reduce network interface energy consumption on these devices: transport-level strategies and application-level strategies. Simulation experiments of transport-level strategies show that the dominant cost comes not from the number of packets sent or received by a particular transport protocol but the amount of time that the NI is in an active but idle state. Simulation experiments of application-level strategies show that significant energy savings can be made with a minimum of user-visible latency." } @Article{saty97, author = "M. Satyanarayanan", title = "Mobile Computing: Where's the Tofu?", journal = "Mobile computing and communications review", year = 1997, volume = 1, number = 1, pages = "17-21", entered-by = "Henry Berg", abstract = "A general article on recent research in mobile computing, focuses on the challenges to be faced and any possible insights to offer the field of computer science. Covers constraints of mobility, adaptation strategies and several other areas." } @InProceedings{fran97, author = "L. Francis", title = "Mobile computing-a fact in your future", key = "DP industry; laptop computers; personal computing; technological forecasting; teleworking; wireless LAN; mobile computing; future; laptop computers; telecommuting; mobile PC; wired systems; dial-up lines; wireless connections; cellphone-like radio links; interaction speed; functionality", pages = "63-7", booktitle = "15th Annual International Conference on Computer Documentation Conference Proceedings. SIGDOC '97. Crossroads in Communication", year = 1997, entered-by = "Henry Berg", abstract = "Mobile computing is now at the stage where cell phones were 5-7 years ago. Laptops are frequently the choice of telecommuters who put in significant amounts of time both at home and at the office, but there is a growing group of mobile users who work from more than two locations and who expect to perform their full job responsibilities using a laptop that rarely returns to the main office. Although a mobile PC can be used without ever connecting to a network, they are typically connected with or without wires. Wired systems are most common and generally use modems with the dial-up lines found in homes or hotels. Wireless connections are increasing in popularity and use cellphone-like radio links to send and receive information, but mobile computing is not just about wireless connections; it is also about using your laptop in a hotel (in any country), at home, in a branch office or at a customer site. Using a laptop in those locations frequently reduces your interaction speed and range of functions to an unacceptable level, but recent improvements have attacked these problems. To really feel the freedom offered by mobile computing, imagine setting up overseas in your customer's spare office and working as if you were in your own office. Imagine being in a foreign country and not having to load printer drivers for each printer and load US fonts for each job in order to produce properly printed output. If this sort of future appeals to you, you're not alone. A likely and growing group is people who already use laptops. In 1996, laptops comprised 30-35% of new PCs sold, and in 1997, 72 million PCs are forecast to be manufactured." } @Article{weis93, author = "M. Weiser", title = "Hot topics-ubiquitous computing", key = "microcomputers; personal computing; technological forecasting; personal computing; ubiquitous computing; unobtrusive technology; personal computer; computing access", journal = "Computer", year = 1993, volume = 26, number = 10, pages = "71-2", month = "Oct", entered-by = "Henry Berg", abstract = "The author suggests that, due to the trends of unobtrusive technology and more intrusive information, the next phase of computing technology will develop nonlinearly. He states that, in the long run, the personal computer and the workstation will become practically obsolete because computing access will be everywhere: in the walls, on your wrist, and in 'scrap' computers (i.e., like scrap paper) lying about to be used as needed. The current research on ubiquitous computing is reviewed." } @InProceedings{scho97, author = "C. Scholefield", title = "Mobile telecommunications and nomadic computing in Asia", key = "cellular radio; computer networks; digital radio; personal communication networks; mobile telecommunications; nomadic computing; Asia; Microelectronics and Computer Technology Corporation; strategic technology benchmarking; personal digital cellular; PDC; personal handyphone system; PHS; third generation research activities; fourth generation wireless networks", volume = 2, pages = "908-12", booktitle = "1997 IEEE 6th International Conference on Universal Person Communications Record. Bridging the Way to the 21st Century, ICUPC '97. Conference Record (Cat. No.97TH8255)", year = 1997, entered-by = "Henry Berg", abstract = "In November 1996 a number companies joined together with a research consortium known as the Microelectronics and Computer Technology Corporation (MCC) to form a North American team on a strategic technology benchmarking tour of Asia. The team met with several companies and government authorities. This paper describe the state-of-the art and anticipated future trends observed during the tour. In particular we found high growth in both personal digital cellular (PDC) and the personal handyphone system (PHS) which are projected to reach 50 million subscribers by 2000. We also gained insights into third generation research activities and a road map to fourth generation wireless networks." } @Article{leon96, author = "U. Leonhardt and J. Magee and P. Dias", title = "Location service in mobile computing environments", key = "authorisation; data privacy; file servers; network operating systems; location service; mobile computing environments; location sensing systems; location information; desktop users; scaleable ubiquitous location service; hierarchy-based access control policies; privacy; visualization", journal = "Computers & Graphics", year = 1996, volume = 20, number = 5, pages = "627-32", entered-by = "Henry Berg", abstract = "With the advent of mobile computing devices and cheap location sensing systems, location information has become an important resource both for mobile and desktop users'. In this paper, we describe some key concepts that a scaleable ubiquitous location service should be based on. Firstly, we show how such a service can accommodate multiple location sensing systems. Secondly, we discuss hierarchy-based access control policies as a flexible and powerful mechanism to protect users' privacy. Thirdly, we address some issues concerning the visualization of location information." } @InProceedings{tera97, author = "Y. Teranishi and F. Tanemo and Y. Umemoto", title = "Dynamic object recomposition for active information system on mobile environment", key = "active databases; deductive databases; Internet; mobile communication; object-oriented methods; portable computers; dynamic object recomposition; active information system; mobile environment; location-dependent information service;", pages = "220-8", booktitle = "Proceedings IDEAS '97. International Database Engineering and Applications Symposium (Cat. No.97TB100166)", year = 1997, entered-by = "Henry Berg", abstract = "Location-dependent information service requires an ability to change both the information and functions provided to the mobile client according to user location and time of access. The paper describes a framework for location dependent information service, called the mobile object model. In the mobile object model, a service consists of objects that contain both information and functions. These objects, called mobile objects, are managed as distributed objects. Mobile objects are recomposed to a composite object according to user status dynamically. This composite object is then executed to realize location-dependent information service. We also propose an architecture based on the model. The architecture reduces the load of network transmission and the amount of CPU power used by the mobile client. Finally, we present a prototype system developed on the WWW called LODIS." } @Article{schn95, author = "J. L. Schnase and E. L. Cunnius", title = "The StudySpace Project: collaborative hypermedia in nomadic computing environments", key = "asynchronous transfer mode; biomedical education; computer aided instruction; electronic mail; groupware; hypermedia; medical computing; multimedia communication; personal computing; wireless LAN; StudySpace Project; collaborative hypermedia; multi-platform nomadic computing environments; health sciences education; synchronous information personalization; information use; LiveBoards; mobile computers; ATM networks; wireless LAN; Lotus Notes; spatial boundaries; temporal boundaries; shared databases; private databases; interdocument linking; information structuring; continued information evolution; asynchronous interactions; discussion group databases; integrated hypermedia mail facility; mobile interface", journal = "Communications of the ACM", year = 1995, volume = 38, number = 8, pages = "72-3", month = "Aug", entered-by = "Henry Berg", abstract = "The StudySpace Project at Washington University School of Medicine is bringing together an assortment of computing and communications technologies to address the challenges of health sciences education. Collaborative hypermedia is the key integrating technology, and our goal is to provide effective any-time/any-place use of information. In StudySpace, we are using LiveBoards, mobile computers, ATM networks and wireless LANs. Lotus Notes is the primary software system. Spatial and temporal boundaries are reduced by using Notes shared and private databases, while interdocument linking allows the structuring, personalization and continued evolution of information. Asynchronous interactions over this material among developers, students and teachers is supported by Notes' discussion group databases and integrated hypermedia mail facility. However, our experience with current releases of Lotus Notes raises two important design issues that future systems must address in multiplatform, nomadic computing environments: (1) mobile interfaces,and (2) synchronous personalization" } @Article{wood97a, author = "K. R. Wood and T. Richardson and F. Bennett", title = "Global teleporting with Java: toward ubiquitous personalized computing", key = "authoring languages; graphical user interfaces; Internet; object-oriented languages; personal computing; global teleporting; Java; ubiquitous personalized computing; mobile computing; personal computing; intermittent network connectivity; Olivetti; Oracle Research Laboratory; mobile applications; LAN; Internet; X Windows", journal = "Computer", year = 1997, volume = 30, number = 2, pages = "53-9", month = "Feb", entered-by = "Henry Berg", abstract = "The essence of mobile computing is having your personal computing environment available wherever you happen to be. Traditionally, this is achieved by physically carrying a computing device (say, a laptop or PDA) which may have some form of intermittent network connectivity, either wireless or tethered. However, at the Olivetti and Oracle Research Laboratory, we have introduced another form of mobility in which it is the user's applications that are mobile. Users do not carry any computing platform but instead bring up their applications on any nearby machine exactly as they appeared when last invoked. We call this form of mobility teleporting, and it has been used continuously and fruitfully by many members of our laboratory. We are extending this idea from our LAN to the entire Internet using Java as the common interface. It is still our personal X sessions that are made mobile, but now they can appear anywhere on the Internet within any Java-enabled browser." } @Article{fitz93, author = "G. W. Fitzmaurice", title = "Situated information spaces and spatially aware palmtop computers", key = "notebook computers; user interfaces; virtual reality; virtual reality; user interfaces; computer-augmented environments; Chameleon prototype; palmtop computers; high-fidelity monitor; computer-synthesized information spaces; 3D input controller; output display", journal = "Communications of the ACM", year = 1993, volume = 36, number = 7, pages = "38-49", month = "Jul", entered-by = "Henry Berg", abstract = "Explores and uncovers a wide range of issues surrounding computer-augmented environments. The Chameleon prototype and a set of computer-augmented applications are described. Chameleon is a prototype system under development at the University of Toronto. It is part of an investigation on how palmtop computers designed with a high-fidelity monitor can become spatially aware of their location and orientation and serve as bridges or portholes between computer-synthesized information spaces and physical objects. In this prototype design, a 3D input controller and an output display are combined into one integrated unit." } @InProceedings{smit97, author = "G. J. M. Smit and P. J. M. Havinga and D. van Os", title = "The Harpoon security system for helper programs on a Pocket Companion", key = "operating systems (computers); portable computers; security of data; utility programs; wireless LAN; Harpoon security system; helper programs; Pocket Companion; wireless hand-held computer; service program; asynchronous interaction; mobile computing; network conditions; prototype; Inferno operating system", pages = "231-8", booktitle = "Proceedings. 23rd Euromicro Conference: New Frontiers of Information Technology (Cat. No.97TB100167)", year = 1997, entered-by = "Henry Berg", abstract = "We present a security framework for executing foreign programs, called helpers, on a Pocket Companion: a wireless hand-held computer. A helper program as proposed in this paper is a service program that can migrate once from a server to a Pocket Companion or vice-versa. A helper program is convenient, provides environment awareness and allows asynchronous interaction. Moreover helpers can be used to save processing power and to reduce communication. By migrating to the location of a resource, a helper can access the resource more efficiently. This is particularly attractive for mobile computing, where the network conditions can be poor and unreliable, and because it does not require a permanent connectivity. Security is a significant concern for helpers, as the user of a Pocket Companion receiving a piece of code for execution may require strong assurances about the helper's behaviour. The best way to achieve a high security is to use a combination of several methods. We are designing a prototype of a helper system, called Harpoon, on top of the Inferno operating system." } @Article{atki89, author = "R. Atkinson and A. Demers and C. Hauser and C. Jacobi and P. Kessler and M. Weiser", title = "Experiences creating a Portable Cedar", key = "high level languages; program compilers; software portability; Portable Cedar; machine-dependent C code; intermediate language; language-independent layer; Portable Common Runtime; Cedar-specific runtime code; Cedar language; portability; compiler; Unix operating system; performance measures", journal = "SIGPLAN Not. (USA), SIGPLAN Notices", year = 1989, volume = 24, number = 7, pages = "322-8", entered-by = "Henry Berg", abstract = "The authors have recently re-implemented the Cedar language to make it portable across many different architectures. The strategy was, first, to use machine-dependent C code as an intermediate language, second, to create a language-independent layer known as the Portable Common Runtime, and third, to write a relatively large amount of Cedar-specific runtime code in a subset of Cedar itself. The paper presents a brief description of the Cedar language, the portability strategy for the compiler and runtime, the manner of making connections to other languages and the Unix operating system, and some performance measures of the Portable Cedar." } @TechReport{sher97, author = "D. Sherertz and M. Tuttle and R. Carlson and R. Acuff and L. Fagan", title = "Mobile Pen-based Access to Knowledge: Prototype for Pen-Based, Handheld, Wireless PC Access to PDQ and CANCERLIT Databases", institution = "Lexical Technology, Inc. & Stanford University", year = 1997, entered-by = "Henry Berg", abstract = {National Cancer Institute SBIR Contract N43-CO-33066 Phase I final report. SBIR topic no. 165: Prototype fr Pen-Based, Handheld, Wireless PC Access to PDQ and CANCERLIT Databases} } @InProceedings{acuf97, author = "R. Acuff and L. Fagan and T. Rindfleisch and B. Levitt and P. Ford", title = "Lightweight, Mobile E-Mail for Intra-Clinic Communication", pages = "729-33", booktitle = "Proceedings of the 1997 AMIA Annual Fall Symposium", year = 1997, month = "Oct", entered-by = "Henry Berg" } @InProceedings{stra96, author = "J. Strain and R. Felciano and A. Seiver and R. Acuff and L. Fagan", title = "Optimizing Physician Access to Surgical Intensive Care Unit Laboratory Information through Mobile Computing", pages = "812-6", booktitle = "Proceedings of the 1996 AMIA Annual Fall Symposium", year = 1996, entered-by = "Henry Berg", month = "October" } @Article{poon96, author = "A. Poon and L. Fagan and E. Shortliffe", title = "The PEN-Ivory Project: Exploring User-Interface Design for the Selection of Items from Large Controlled Vocabularies of Medicine", journal = "Journal of the American Medical Informatics Association", year = 1996, volume = 3, number = 2, entered-by = "Henry Berg", pages = "168-83" } @InProceedings{ram94, author = "R. Ram and B. Block", title = "Development of a portable information system: connecting palmtop computers with medical records systems and clinical reference resources", key = "Hewlett Packard computers; integrated software; medical information systems; microcomputer applications; notebook computers; records management; security of data; portable information system; Hewlett-Packard 95LX palmtop computer; MUMPS; clinical reference resources; physicians; medical information systems; family health center; hospital information system; Automated Ambulatory Medical Record System; confidentiality; password protection; data downloading; database; patient summary data; family practice programme; palmtop memory card updating; integrated software package; information management software; to-do lists; reliability; decision support software; security", pages = "125-128", booktitle = "Seventeenth Annual Symposium on Computer Applications in Medical Care. Patient-Centered Computing", year = 1994, publisher = "McGraw-Hill", entered-by = "Henry Berg", abstract = "The portability of palmtop computers makes them an ideal platform to maintain communication between busy physicians and medical information systems (MIS). In our academic FHC (Family Health Center), we have developed software that runs on a palmtop computer allowing access to information in the hospital information system and our FHC's AAMRS (Automated Ambulatory Medical Record System). Using a Hewlett-Packard 95LX palmtop computer, custom software has been developed to access summary data on in-patients and out-patients. Data is downloaded into a database on a palmtop computer memory card. ASCII data from a MIS is transformed into a database format readable on the palmtop. Our hospital MIS department transmits information daily on our in-patient service. We also download, weekly, a patient summary on all of our active out-patients in our MUMPS-based AAMRS. Each morning, the resident in the Family Practice program updates his palmtop memory card at a central workstation. We have made the palmtop computer even more valuable to physicians by providing an integrated software package. This package includes information management software with to-do lists, reference software such as drug formularies and decision support software. The downloading of patient information creates two important problems: security and reliability. To assure the confidentiality of downloaded patient information, the palmtop system uses password protection." } @Article{ster96, author = "B. Sterzbach and W.A. Halang", title = "A mobile vehicle on-board computing and communication system", key = "cellular radio; computerised control; data visualisation; geography; Global Positioning System; position control; satellite tracking; vehicles; mobile vehicle on-board computing; communication system; DuO vehicle tracking; fleet management system; mobile computing application; geographical information visualization; control centre; on-board unit; GPS positioning; GSM data communication", journal = "Computers & Graphics, vol.20, no.5, p. 659-67", year = 1996, volume = 20, number = 5, pages = "659-67", entered-by = "Henry Berg", abstract = "The DuO vehicle tracking and fleet management system is presented as an example for a mobile computing application. The paper focuses on the visualization of geographical information at a control centre, on the design of the on-board unit and on the interaction and communication between the on-board units and the control centre. The technologies of GPS positioning and GSM data communication are presented as they are used within the system." } @Article{thom96a, author = "P. J. Thomas and J. F. Meech and J. Williams", title = "Multimedia information using mobile computers: accessing the digital campus and the digital library", key = "computer aided instruction; electronic publishing; information needs; information networks; library automation; multimedia systems; personal information systems; technological forecasting; wireless LAN; multimedia information; mobile computers; digital campus; digital library; global digital medium; information resource; digital publishing; online information delivery; library services; Internet; digital bookshop; rich multimedia data; information services; IT ubiquistructure; scholarly activities; teaching activities; interactive user access; digital classroom; SuperJANET; traditional media; personal technology; digital information; paper-based information; 140 Mbit/s", journal = "New Review of Hypermedia and Multimedia, Applications and Research", year = 1996, volume = 2, pages = "17-23", entered-by = "Henry Berg", abstract = "The role of the information resource is changing. Publishers have been slow to adapt to the emergence of a global digital medium, but there are now signs that a great deal of information will be delivered online. However, digital publishing on the Internet with services for libraries will be a driving force in creating the global digital medium. One issue that will become increasingly relevant is how the individual user accesses rich multimedia data in the most appropriate way. The digital university campus and the digital library are becoming important concepts, with the aim that users of information services will receive information online supported by a ubiquistructure' of IT. For the digital campus, this means that scholarly and teaching activities are based on interactive access to information, and that the digital bookshop and the digital classroom are becoming possible with the development of 140 Mb/s SuperJANET links. However, libraries will not be truly digital for the foreseeable future, and they will maintain traditional and digital media side by side. We look at the digital library and the digital campus from the perspective of the individual user and his information needs. We are particularly interested in the use of small, mobile computers as access points to the global digital medium. In an environment of change (where the traditional campus and library exist alongside the digital campus and library), the most appropriate form of access technology is based on personal technology, which allows linking between digital information and traditional paper-based information." } @Article{citr96, author = "W. V. Citrin and M. D. Gross", title = "PDA-based graphical interchange for field service and repair workers", key = "distributed processing; electronic data interchange; engineering graphics; inter-computer links; maintenance engineering; notebook computers; service industries; visual databases; PDA-based graphical interchange; field service workers; field repair workers; central database; updated database; diagram recognition functionality; handwriting recognition; shape recognition; domain-based diagram recognition; off-line drawing recognition", journal = "Computers & Graphics, vol.20, no.5, p. 641-9", year = 1996, volume = 20, number = 5, pages = "641-9", entered-by = "Henry Berg", abstract = "We present an ongoing project to develop a system to provide field service workers with timely and accurate service information. The system will allow workers to download diagrams or photographs from a host computer's central database onto a PDA. The workers will be able to annotate the diagrams to reflect work performed, and later upload the annotations to the host computer, where they will be integrated into an updated database. Diagram recognition functionality is distributed between the PDA (which performs low-level shape and handwriting recognition) and the host computer (which performs high-level domain-based diagram recognition). Distributing the functionality offers a number of advantages: it allows the relatively resource-poor PDA to be part of a powerful diagram recognition environment, it allows the use of standardized hardware-based recognition facilities in a domain-based recognition system, and it allows off-line drawing recognition and storage of diagrams, thereby avoiding excessive use of slow or expensive communications channels." } @Article{weis93a, author = "M. Weiser", title = "Some computer science issues in ubiquitous computing", key = "computer networks; data privacy; user interfaces user interfaces; computer science; ubiquitous computing; hardware components; network protocols; interaction; applications; privacy; computational methods", journal = "Communications of the ACM", year = 1993, volume = 36, number = 7, pages = "74-84", entered-by = "Henry Berg", abstract = "Ubiquitous computing enhances computer use by making many computers available throughout the physical environment, while making them effectively invisible to the user. This article explains what is new and different about the computer science involved in ubiquitous computing. First, it provides a brief overview of ubiquitous computing, then elaborates through a series of examples drawn from various subdisciplines of computer science: hardware components (e.g. chips), network protocols, interaction substrates (e.g. software for screens and pens), applications, privacy, and computational methods. Ubiquitous computing offers a framework for new and exciting research across the spectrum of computer science." } @Article{weis91, author = "M. Weiser", title = "The computer for the 21st century", key = "microcomputers; office automation; personal computing; social aspects of automation personal computers; laptop machines; dynabooks; knowledge navigators; information technology", journal = "Scientific American (International Edition)", year = 1991, volume = 265, number = 3, pages = "66-75", entered-by = "Henry Berg", abstract = "The arcane aura that surrounds personal computers is not just a 'user interface' problem. The idea of a 'personal' computer itself is misplaced and that the vision of laptop machines, dynabooks and knowledge navigators is only a transitional step toward achieving the real potential of information technology. Such machines cannot truly make computing an integral, invisible part of people's lives. The author and his colleagues are therefore trying to conceive a new way of thinking about computers, one that takes into account the human world and allows the computers themselves to vanish into the background." } @Article{want95, author = "R. Want and B. N. Schilit and N. I. Adams and R. Gold and K. Petersen and D. Goldberg and J. R. Ellis and M. Weiser", title = "An overview of the PARCTAB ubiquitous computing experiment", key = "context-sensitive languages; data communication; mobile communication; notebook computers; office automation; optical communication; wireless LAN; PARCTAB ubiquitous computing experiment; palm-sized mobile computer; office network; Xerox PARC; computing environment; context sensitivity; casual interaction; spatial arrangement; user interface issues", journal = "IEEE Personal Communications", year = 1995, volume = 2, number = 6, pages = "28-33", month = "Dec", entered-by = "Henry Berg", abstract = "The PARCTAB system integrates a palm-sized mobile computer into an office network. The PARCTAB project serves as a preliminary testbed for ubiquitous computing, a philosophy originating at Xerox PARC that aims to enrich our computing environment by emphasizing context sensitivity, casual interaction and the spatial arrangement of computers. This article describes the ubiquitous computing philosophy, the PARCTAB system, user interface issues for small devices, and our experience in developing and testing a variety of mobile applications." } @InProceedings{bumi93, author = "J. Bumiller and S. Rather", title = "Electronic meeting assistance", key = "groupware; local area networks; office automation; Electronic Meeting Assistance; meeting; local area network; personal Notepads; radio LAN; interactive white-board; Xerox LiveBoard; cooperative work; contact information; prepared notes; electronic presentations", pages = "425-6", booktitle = "Human Computer Interaction. Vienna Conference, VCHCI '93 Fin de Siecle Proceedings", year = 1993, month = "Sep", entered-by = "Henry Berg", abstract = "The Electronic Meeting Assistance (EMA) is a virtually co-located mixed system. That means that all participants of the meeting are present at the same time but not necessary at the same location (for example some people meet in a room and an external, remote expert is included via a local area network). During the meeting the personal Notepads of the participants are linked together using a radio LAN. In addition an interactive white-board e.g. the Xerox LiveBoard is used for visualisation and manipulation of common data. To assist cooperative work, the EMA system supports the exchange of information during meetings. Various information can be exchanged between meeting members, for example contact information, prepared notes and diagrams; electronic presentations could be given or a paper could be edited by the group." } @InProceedings{mora95, author = "T. P. Moran and P. Chiu and W. van Melle and G. Kurtenbach", title = "Implicit structures for pen-based systems within a freeform interaction paradigm", key = "character recognition equipment; data structures; interactive devices; list processing; notebook computers; user interfaces; implicit structures; pen-based whiteboard system; freeform interaction paradigm; Tivoli; Xerox LiveBoard; structured editing capability; free expression; ease of use; list structures; text structures; table structures; outline structures; handwritten scribbles; typed text; WYPIWYG capability; perceptual suppport; user interface design; informal systems; recognition-based systems; gestural interfaces; groupware", pages = "487-94", booktitle = "Human Factors in Computing Systems. CHI'95 Conference Proceedings", year = 1995, entered-by = "Henry Berg", abstract = {Presents a scheme for extending an informal, pen-based whiteboard system (Tivoli on the Xerox LiveBoard) to provide a structured editing capability without violating its free expression and ease of use. The scheme supports list, text, table and outline structures over handwritten scribbles and typed text. The scheme is based on the system temporarily perceiving the implicit structure that humans see in the material, which is called a WYPIWYG (what you perceive is what you get) capability. The design techniques, principles, trade-offs and limitations of the scheme are discussed. A notion of "freeform interaction" is proposed to position the system with respect to current user interface techniques.} } @InProceedings{welc94, author = "B. Welch and S. Elrod and T. Moran and K. McCall and F. Halasz and R. Bruce", title = "Applications of a computerized whiteboard", key = "computer displays; interactive systems; light pens; liquid crystal displays; multimedia systems; computerized whiteboard; infrared pen technology; rear projected liquid crystal light valve; group station; computational tools; whiteboard metaphor; multimedia presentation tool; communication device; remotely shared work surface; interactive display surface; LiveBoard", pages = "591-3", booktitle = "1994 SID International Symposium Digest of Technical Papers. SID", year = 1994, entered-by = "Henry Berg", abstract = "A computerized whiteboard has been built using an infrared pen technology in combination with a 67 inch display. The image is formed from a rear projected liquid crystal light valve. The system was designed to support several different applications: a whiteboard that enables both capture and organization of information for informal creative meetings, a group station where computational tools can be used through the whiteboard metaphor, a communication device employing a remotely shared work surface, and a multimedia presentation tool." } @InProceedings{kant93, author = "C. K. Kantarjiev and A. Demers and R. Frederick and R. T. Krivacic and M. Weiser", title = "Experiences with X in a wireless environment", key = "graphical user interfaces; local area networks; mobile radio systems; network operating systems; X Window System; location-independent computing; wireless environment; personal display assistants; graphical user interface; server implementation strategies; MPad system; wireless local area network; hand-held wireless computing devices; media access protocol", pages = "117-28", booktitle = "Proceedings of the USENIX Mobile and Location-Independent Computing Symposium", year = 1993, month = "Aug", entered-by = "Henry Berg", abstract = "Wireless computing is all the rage; the X Window System seems to be inescapable. We have been experimenting with the cross-product, and have had mixed results. The network may not be the computer any more, but it certainly influences the way the computer performs, and adding a fairly atypical network layer cannot help but expose some underlying assumptions. We discuss a few that we found and go on to speculate about how to best push X in the direction of mobile and location-independent computing." } @Book{wear97, title = "Digest of Papers. First International Symposium on Wearable Computers (Cat. No.97TB100199)", year = 1997, key = "wearable computers", entered-by = "Henry Berg", month = "Oct" } @InProceedings{kn:icad96, author = "Frankie James", title = "Presenting HTML Structure in Audio: User Satisfaction with Audio Hypertext", pages = "97--103", booktitle = "ICAD '96 Proceedings", year = 1996, organization = "ICAD", publisher = "Xerox PARC", month = "November", note = "Also appeared in Web Techniques entitled Experimenting with Audio Interfaces, February 1998, vol 3 no 2, pages 55--58" } @TechReport{kn:cslitr, author = "Frankie James", title = "Presenting HTML Structure in Audio: User Satisfaction with Audio Hypertext", institution = "Stanford University", year = 1997, type = "CSLI Technical Report", number = "97-201", note = "Available at http://dbpubs.stanford.edu/pub/1996-83", links = "(title:www:http://dbpubs.stanford.edu/pub/1996-83)" } @InProceedings{kn:www6, author = "Frankie James", title = "AHA: Audio HTML Access", editor = "Michael R. Genesereth and Anna Patterson", pages = "129--140", booktitle = "Proceedings of the Sixth International World Wide Web Conference. Published in Computer Networks and ISDN Systems, vol.29, no.8-13, p. 1395-404, 0169-7552 Elsevier Sept. 1997 ", year = 1997, organization = "IW3C", address = "Santa Clara, CA", month = "April" } @InProceedings{kn:as98, author = "Frankie James", title = "Lessons from Developing Audio HTML Interfaces", pages = "27--34", booktitle = "ASSETS 98", year = 1998, organization = "ACM SIGCAPH", address = "Marina del Rey, CA", month = "April" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-45)" } @ARTICLE{KSS97 ,AUTHOR = "H. Kautz and B. Selman and and M. Shah" ,TITLE = "Referral Web: Combining Social Networks and collaborative Filtering" ,JOURNAL = cacm ,YEAR = "1997" ,month = "March" ,volume = "40" ,number = "3" ,pages = "63-65" ,entered-by = "Junghoo Cho" ,abstract = { One of the most effective channels for disseminating information and expertise within an organization is its informal social network of collaborators, colleagues and friends. Manually searching for a referral chain can be a frustrating and time-consuming task. One is faced with the trade-off of contacting a large number of individuals at each step, and thus straining both the time and goodwill of the possible respondents, or of contacting a smaller, more focused set, and being more likely to fail to locate an appropriate expert. In response to these problems, we are building ReferralWeb, an interactive system for reconstructing, visualizing and searching social networks on the World Wide Web. Simulation experiments we ran before we began construction of ReferralWeb showed that automatically generated referrals can be highly successful in locating experts in a large network. } } @INPROCEEDINGS{RISBR94 ,AUTHOR = "P. Resnick and N. Iacovou and M. Suchak and P. Bergstrom and J. Riedl" ,TITLE = "GroupLens: an open architecture for collaborative filtering of netnews" ,BOOKTITLE = "Proceedings of the Conference on Computer Supported Collaborative Work" ,YEAR = "1994" ,publisher = "Transcending Boundaries" ,entered-by = "Junghoo Cho" ,abstract = { Collaborative filters help people make choices based on the opinions of other people. GroupLens is a system for collaborative filtering of netnews, to help people find articles they will like in the huge stream of available articles. News reader clients display predicted scores and make it easy for users to rate articles after they read them. Rating servers, called Better Bit Bureaus, gather and disseminate the ratings. The rating servers predict scores based on the heuristic that people who agreed in the past will probably agree again. Users can protect their privacy by entering ratings under pseudonyms, without reducing the effectiveness of the score prediction. The entire architecture is open: alternative software for news clients and Better Bit Bureaus can be developed independently and can interoperate with the components we have developed. } } @ARTICLE{KMMHGR97 ,AUTHOR = "J.A. Konstan and B.N. Miller and D. Maltz and J.L. Herlocker and L.R. Gordon and J. Riedl" ,TITLE = "GroupLens: Applying Collaborative Filtering to Usenet News" ,JOURNAL = cacm ,YEAR = "1997" ,month = "March" ,volume = "40" ,number = "3" ,pages = "77-87" ,entered-by = "Junghoo Cho" ,abstract = {The GroupLens project designed, implemented and evaluated a collaborative filtering system for Usenet news-a high-volume, high-turnover discussion list service on the Internet. Usenet newsgroups (the individual discussion lists) may carry hundreds of messages each day. The combination of high volume and personal taste made Usenet news a promising candidate for collaborative filtering. More formally, we determined that the potential predictive utility for Usenet news was very high. GroupLens has proved to be an experimental success and it shows promise as a viable service for all Usenet news users. } } @INPROCEEDINGS{MRK97 ,AUTHOR = "B. Miller and J. Riedl and J. Konstan" ,TITLE = "Experiences with GroupLens: Making Usenet useful again" ,BOOKTITLE = "Proceedings of Usenix Winter Technical 1997 Conference" ,YEAR = "1997" ,entered-by = "Junghoo Cho" } @ARTICLE{GNOT92 ,AUTHOR = "D. Goldberg and D. Nichols and B.M. Oki and D. Terry" ,TITLE = "Using collaborative filtering to weave an information tapestry" ,JOURNAL = cacm ,YEAR = "1992" ,volume = "35" ,number = "12" ,pages = "61-70" ,entered-by = "Junghoo Cho" ,abstract = {Tapestry is an experimental mail system developed at the Xerox Palo Alto Research Center. The system manages an in-coming stream of electronic documents, including E-mail, newswire stories and NetNews articles. The system implements a novel mechanism for collaborative filtering in which users annotate documents before the documents art filtered. Because annotations are not available at the time a new document arrives, the system supports continuous queries that examine the entire database of documents and take into account newly introduced annotations during the filtering process. } } @INPROCEEDINGS{HSRF95 ,AUTHOR = "W. Hill and L. Stead and M. Rosenstein and G. Furnas" ,TITLE = "Recommending and evaluating choices in a virtual community of use" ,BOOKTITLE = chi95 ,YEAR = "1995" ,publisher = "ACM" ,address = "New York" ,entered-by = "Junghoo Cho" ,abstract = {When making a choice in the absence of decisive first-hand knowledge, choosing as other like-minded, similarly-situated people have successfully chosen in the past is a good strategy-in effect, using other people as filters and guides: filters to strain out potentially bad choices and guides to point out potentially good choices. Current human-computer interfaces largely ignore the power of the social strategy. For most choices within an interface, new users are left to fend for themselves and if necessary, to pursue help outside of the interface. We present a general history-of-use method that automates a social method for informing choice and report on how it fares in the context of a fielded test case: the selection of videos from a large set. The positive results show that communal history-of-use data can serve as a powerful resource for use in interfaces. } } @INPROCEEDINGS{MAEH95 ,AUTHOR = "D. Maltz and K. Ehrlich" ,TITLE = "Pointing the way: Active collaborative filtering" ,BOOKTITLE = chi95 ,YEAR = "1995" ,publisher = "ACM" ,address = "New York" ,entered-by = "Junghoo Cho" ,abstract = {Collaborative filtering is based on the premise that people looking for information should be able to make use of what others have already found and evaluated. Current collaborative filtering systems provide tools for readers to filter documents based on aggregated ratings over a changing group of readers. Motivated by the results of a study of information sharing, we describe a different type of collaborative filtering system in which people who find interesting documents actively send "pointers" to those documents to their colleagues. A "pointer" contains a hypertext link to the source document as well as contextual information to help the recipient determine the interest relevance of the document prior to accessing it. Preliminary data suggest that people are using the system in anticipated and unanticipated ways, as well as creating information digests. } } @INPROCEEDINGS{MOSH94 ,AUTHOR = "M. Morita and Y. Shinoda" ,TITLE = "Information filtering based on user behavior analysis and best match text retrieval" ,BOOKTITLE = "Proceedings of 17th International Conference on Research and Development in Information Retrieval" ,YEAR = "1994" ,publisher = "ACM" ,address = "New York" ,entered-by = "Junghoo Cho" ,abstract = {Information filtering systems have potential power that may provide an efficient means of navigating through a large and diverse data space. However, current information filtering technology heavily depends on a user's active participation for describing his interest in information items, forcing him to accept an extra load to overcome the already loaded situation. Furthermore, because the user's interests are often expressed in a discrete format, such as a set of keywords, sometimes augmented with if-then rules, it is difficult to express ambiguous interests, which users often want to do. We propose a technique that uses user behavior monitoring to transparently capture the user's information interests, and a technique to use these interests to filter incoming information in a very efficient way. It is verified by conducting a field experiment and a series of simulations that the proposed techniques perform very well. } } @INPROCEEDINGS{SHMA95 ,AUTHOR = "U. Shardanand and P. Maes" ,TITLE = "Social information filtering: Algorithms for automating ``word of mouth.''" ,BOOKTITLE = chi95 ,YEAR = "1995" ,publisher = "ACM" ,address = "New York" ,entered-by = "Junghoo Cho" ,abstract = {We describe a technique for making personalized recommendations from any type of database to a user based on similarities between the interest profile of that user and those of other users. In particular, we discuss the implementation of a networked system called Ringo, which makes personalized recommendations for music albums and artists. Ringo's database of users and artists grows dynamically as more people use the system and enter more information. Four different algorithms for making recommendations by using social information filtering were tested and compared. We present quantitative and qualitative results obtained from the use of Ringo by more than 2000 people. } } @INPROCEEDINGS{LIEB95 ,AUTHOR = "Henry Lieberman" ,TITLE = "Letizia: An Agent that Assists Web Browsing" ,BOOKTITLE = "Proceedings of 14th International Joint Conference on Artificial Intelligence" ,YEAR = "1995" ,editor = "C.S. Mellish" ,entered-by = "Junghoo Cho" ,abstract = {Letizia is a user interface agent that assists a user browsing the World Wide Web. As the user operates a conventional Web browser such as Netscape, the agent tracks user behaviour and attempts to anticipate items of interest by doing concurrent, autonomous exploration of links from the user's current position. The agent automates a browsing strategy consisting of a best first search augmented by heuristics inferring user interest from browsing behaviour. } } @ARTICLE{MAES94 ,AUTHOR = "P. Maes" ,TITLE = "Agents that reduce work and information overload" ,JOURNAL = cacm ,YEAR = "1994" ,month = "July" ,volume = "37" ,number = "7" ,pages = "30-40" ,entered-by = "Junghoo Cho" ,abstract = {The currently dominant interaction metaphor of direct manipulation requires the user to initiate all tasks explicitly and to monitor all events. This metaphor will have to change if untrained users are to make effective use of the computer and networks of tomorrow. Techniques from the field of AI, in particular so-called "autonomous agents", can be used to implement a complementary style of interaction, which has been referred to as indirect management. Instead of user-initiated interaction via commands and or direct manipulation, the user is engaged in a cooperative process in which human and computer agents both initiate communication, monitor events and perform tasks. The metaphor used is that of a personal assistant who is collaborating with the user in the same work environment. The assistant becomes gradually more effective as it learns the user's interests, habits and preferences (as well as those of his or her community). } } @ARTICLE{MOMA98 ,AUTHOR = "A. Moukas and P. Maes" ,TITLE = "Amalthaea: An Evolving Information Filtering and Discovery System for the WWW" ,JOURNAL = "Journal of Autonomous Agents and Multi-Agent Systems" ,YEAR = "1998" ,entered-by = "Junghoo Cho" ,abstract = {Amalthaea is an evolving, multiagent ecosystem for personalized filtering, discovery and monitoring of information sites. Amalthaea's primary application domain is the World-Wide-Web and its main purpose is to assist its users in finding interesting information. Two different categories of agents are introduced in the system: filtering agents that model and monitor the interests of the user and discovery agents that model the information sources. A market-like ecosystem where the agents evolve, compete and collaborate is presented: agents that are useful to the user or other agents reproduce while low- performing agents are destroyed. Results from various experiments with different system configurations and varying ratios of user interests versus agents in the system are presented. Finally issues like fine-tuning the initial parameters of the system and establishing and maintaining equilibria in the ecosystem are discussed. } } @INPROCEEDINGS{JFM97 ,AUTHOR = "T. Joachims and D. Freitag and T. Mitchell" ,TITLE = "WebWatcher: A Tour Guide for the World Wide Web" ,BOOKTITLE = "Proceedings of IJCAI97" ,YEAR = "1997" ,entered-by = "Junghoo Cho" ,abstract = {We describe WebWatcher as a tour guide agent for the web, the learning algorithms used by WebWatcher, experimental results based on learning from thousands of users, and lessons learned from this case study of tour guide agents. } } @INPROCEEDINGS{AFJM95 ,AUTHOR = "R. Armstrong and D. Freitag and T. Joachims and T. Mitchell" ,TITLE = "WebWatcher: A Learning Apprentice for the World Wide Web" ,BOOKTITLE = "AAAI Spring Symposium on Information Gathering" ,YEAR = "1995" ,entered-by = "Junghoo Cho" ,abstract = {We describe an information seeking assistant for the world wide web. This agent, called WebWatcher, interactively helps users locate desired information by employing learned knowledge about which hyperlinks are likely to lead to the target information. } } @ARTICLE{BASH97 ,AUTHOR = "M. Balabanovic and Y. Shoham" ,TITLE = "Fab: content-based collaborative recommendation" ,JOURNAL = cacm ,YEAR = "1997" ,month = "March" ,volume = "40" ,number = "3" ,pages = "66-72" ,entered-by = "Junghoo Cho" ,abstract = {Online readers are in need of tools to help them cope with the mass of content that is available on the World Wide Web. In traditional media, readers are provided assistance in making selections. This includes both implicit assistance in the form of editorial oversight and explicit assistance in the form of recommendation services such as movie reviews and restaurant guides. The electronic medium offers new opportunities to create recommendation services, ones that adapt over time to track users' evolving interests. Fab is such a recommendation system for the Web, and has been operational in several versions since December 1994. By combining both collaborative and content-based filtering systems, Fab may eliminate many of the weaknesses found in each approach. } } @INPROCEEDINGS{BASH95 ,AUTHOR = "M. Balabanovic and Y. Shoham" ,TITLE = "Learning information retrieval agents: Experiments with automated web browsing" ,BOOKTITLE = "AAAI spring symposium on Information Gathering" ,YEAR = "1995" ,entered-by = "Junghoo Cho" ,abstract = {The current exponential growth of the Internet precipitates a need for new tools to help people cope with the volume of information. To complement recent work on creating searchable indexex of the World-Wide Web and systems for filtering incoming e-mail and Usenet news articles, we describe a system which helps users keep abreast of new and interesting information. Every day it presents a selection of interesting web pages. The user evaluates each page, and given this feedback the system adapts and attempts to produce better pages the following day. We prsent some early results from an AI programming class to whom this was set as a project, and then describe our current implementation. Over the course of 24 days the output of our system was compared to both randomly-selected and human-selected pages. It consistently performed better than the random pages, and was better than the human-selected pages half of the time.} } @INPROCEEDINGS{SKS98 ,AUTHOR = "S. Schechter and M. Krishnan and M. Smith" ,TITLE = "Using path profiles to predict HTTP request" ,BOOKTITLE = "Proceedings of 7th International World Wide Web Conference" ,YEAR = "1998" ,entered-by = "Junghoo Cho" ,abstract = {Webmasters often use the following rule of thumb to ensure that HTTP server performance does not degrade when traffic is its heaviest provide twice the server capacity required to handle your site's average load. As a result the server will spend half of its CPU cycles idle during normal operation. These cycles could be used to reduce the latency of a significant subset of HTTP transactions handled by the server. In this paper we introduce the use of path profiles for describing HTTP request behavior and describe an algorithm for efficiently creating these profiles. We then show that we can predict request behavior using path profiles with high enough probability to justify generating dynamic content before the client requests it. If requests are correctly predicted and pre-generated by the server, the end user will witness significantly lower latencies for these requests.} } @ARTICLE{RUPO97 ,AUTHOR = "J. Rucker and M.J. Polanco" ,TITLE = "Siteseer: personalized navigation for the Web" ,JOURNAL = cacm ,YEAR = "1997" ,month = "March" ,volume = "40" ,number = "3" ,pages = "73-75" ,entered-by = "Junghoo Cho" ,abstract = {Siteseer is a World Wide Web page recommendation system that uses an individual's bookmarks and the organization of bookmarks within folders for predicting and recommending relevant pages. Siteseer utilizes each user's bookmarks as an implicit declaration of interest in the underlying content, and the user's grouping behavior (such as the placement of subjects in folders) as an indication of semantic coherency or relevant groupings between subjects. In addition, Siteseer treats folders as a personal classification system which enables it to contextualize recommendations into classes defined by the user. Over time, Siteseer learns each user's preferences and the categories through which they view the world, and at the same time it learns, for each Web page, how different communities or affinity-based clusters of users regard it. Siteseer then delivers personalized recommendations of online content and Web pages, organized according to each user's folders. } } @ARTICLE{THAMC97 ,AUTHOR = "L. Terveen and W. Hill and B. Amento and D. McDonald and J. Creter" ,TITLE = "PHOAKS: a system for sharing recommendations" ,JOURNAL = cacm ,YEAR = "1997" ,month = "March" ,volume = "40" ,number = "3" ,pages = "59-62" ,entered-by = "Junghoo Cho" ,abstract = {Finding relevant, high-quality information on the World Wide Web is a difficult problem. PHOAKS (People Helping One Another Know Stuff) is an experimental system that addresses this problem through a collaborative filtering approach. PHOAKS works by automatically recognizing, tallying and redistributing recommendations of Web resources mined from Usenet news messages. } } @ARTICLE{FODU92 ,AUTHOR = "P.W. Foltz and S.T. Dumais" ,TITLE = "Personalized information delivery: an analysis of information methods" ,JOURNAL = cacm ,YEAR = "1992" ,month = "December" ,volume = "35" ,number = "12" ,pages = "51-60" ,entered-by = "Junghoo Cho" ,abstract = {With the increasing availability of information in electronic form, it becomes more important and feasible to have automatic methods to filter information. The results of an experiment aimed at determining the effectiveness of four information-filtering methods in the domain of technical reports are presented. The experiment was conducted over a six-month period with 34 users and over 150 new reports published each month. Overall, the authors conclude that filtering methods show promise for presenting personalized information. } } @ARTICLE{LOEB92 ,AUTHOR = "S. Loeb" ,TITLE = "Architecting personalized delivery of multimedia information" ,JOURNAL = cacm ,YEAR = "1992" ,month = "December" ,volume = "35" ,number = "12" ,pages = "39-48" ,entered-by = "Junghoo Cho" ,abstract = {Information filters are essential mediators between information sources and their users. In most cases, both the information sources and the information users possess no mutual knowledge that can guide them in finding the information most relevant for the users' momentary and long-term needs. Filters, which are positioned logically as 'third parties' to the communication between users and sources, should possess both the knowledge and the functionality to examine the information in the sources and to forward the information 'they judge' as relevant to individual users. The author views the information-filtering process as dependent on the application domain in which it operates and on the context in which it is used. An introduction is given to some of the dimensions which can help distinguish the variety of known filtering applications and usage scenarios and a description is given of a novel filtering model for casual users and its implementation in the Lyric-Times personalized music system. This model utilizes a stored long-term user profile and involves time explicitly in its selection criteria. } } @ARTICLE{HIHO94 ,AUTHOR = "W. Hill and J. Hollan" ,TITLE = "History-Enriched Digital Objects: Prototypes and Policy Issues" ,JOURNAL = "The Information Society" ,YEAR = "1994" ,month = "April-June" ,volume = "10" ,number = "2" ,entered-by = "Junghoo Cho" ,abstract = {Recording on digital objects (e. g. reports, forms, contracts, mail-order catalogs, source code, manual pages, email, spreadsheets, menus) the interaction events that comprise their use makes it possible on future occasions, when the objects are used again, to display graphical abstractions of the accrued histories as parts of the objects themselves. For example, co-authors of a report can see stable and unstable sections (lines of text are marked by recency of changes or amount of editing) and identify who has written what and when. In the case of reading documentation, a reader can see who else has previously read a particular section of interest. While using a spreadsheet to refine a budget, the count of edits per spreadsheet cell can be mapped onto grayscale to give an impression of which budget numbers have been reworked the most and least. Or in the context of learning unfamiliar menu selections in a new piece of software, the menu itself can depict the distribution statistics of colleagues' previous menu selections in the same or similar contexts. There are many existing computational devices that hint at the prospect of history-enriched digital objects. Automatic change-bars, citation indices, and download counts on computer bulletin boards are examples. In fact, for the last thirteen years, members of our lab have been able to request AP News articles by specifying a minimum number of previous readers and thus easily retrieve articles that colleagues have chosen to read. } } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% % % Google : Stanford % @INPROCEEDINGS{BRPA98 ,AUTHOR = "S. Brin and L. Page" ,TITLE = "The Anatomy of a Large-Scale Hypertextual Web Search Engine" ,BOOKTITLE = "Proceedings of 7th World Wide Web Conference" ,YEAR = "1998" ,entered-by = "Junghoo Cho" ,abstract = {In this paper, we present Google, a prototype of a large-scale search engine which makes heavy use of the structure present in hypertext. Google is designed to crawl and index the Web efficiently and produce much more satisfying search results than existing systems. The prototype with a full text and hyperlink database of at least 24 million pages is available at http://google.stanford.edu/ To engineer a search engine is a challenging task. Search engines index tens to hundreds of millions of web pages involving a comparable number of distinct terms. They answer tens of millions of queries every day. Despite the importance of large-scale search engines on the web, very little academic research has been done on them. Furthermore, due to rapid advance in technology and web proliferation, creating a web search engine today is very different from three years ago. This paper provides an in-depth description of our large-scale web search engine -- the first such detailed public description we know of to date. Apart from the problems of scaling traditional search techniques to data of this magnitude, there are new technical challenges involved with using the additional information present in hypertext to produce better search results. This paper addresses this question of how to build a practical large-scale system which can exploit the additional information present in hypertext. Also we look at the problem of how to effectively deal with uncontrolled hypertext collections where anyone can publish anything they want. } } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% % % MetaData architecture: PICS, ComMentor % @ARTICLE{REMI96 ,AUTHOR = "P. Resnick and J. Miller" ,TITLE = "PICS: Internet Access Controls Without Censorship" ,JOURNAL = cacm ,YEAR = "1996" ,volume = "39" ,number = "10" ,pages = "87-93" ,entered-by = "Junghoo Cho" ,abstract = {With its recent explosive growth, the Internet now faces a problem inherent in all media that serve diverse audiences: not all materials are appropriate for every audience. Societies have tailored their responses to the characteristics of the media [1, 3]: in most countries, there are more restrictions on broadcasting than on the distribution of printed materials. Any rules about distribution, however, will be too restrictive from some perspectives, yet not restrictive enough from others. We can do better-we can meet diverse needs by controlling reception rather than distribution. In the TV industry, this realization has led to the V-chip, a system for blocking reception based on labels embedded in the broadcast stream. } } @ARTICLE{RWP95 ,AUTHOR = "M. Roscheisen and T. Winograd and A. Paepcke" ,TITLE = "Content Rating and Other Third-Party Value-Added Applications for the World-Wide Web" ,JOURNAL = "D-Lib magazine" ,YEAR = "1995" ,month = "August" ,entered-by = "Junghoo Cho" ,abstract = {Imagine you want to know what your colleagues in the interest group DLissues have found worth seeing lately. In your browser, you select "Tour annotation set DLissues", with the filter set to "annotations newly created since yesterday". You get a report containing pointers to annotated locations in various documents; you inspect some of these links with a comment previewer. Sara evidently appreciated a paper on security in the proceedings of a conference last year--she gave it the highest ranking on her personal scale. You click on the link and jump to the annotated section in the paper. You scan it up and down and wonder whether the security research group you know at another university has any opinion on this paper. You turn on their annotation set SecurityPapers, which you can access free of charge since your school has a site licensing agreement. You see that they have made a "trailmarker annotation" to the top of the paper. You inspect the annotation icon with the previewer: it says that the paper you are viewing is really subsumed now by the one at a more recent conference which the trail marker points to. With another click you jump to this more recent paper, which turns out to be written even more clearly. You go back to reply to Sara's original comment and include a pointer to the SecurityPapers set. } } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% % % WebGlimpse : U of Arizona % @INPROCEEDINGS{MSG97 ,AUTHOR = "U. Manber and M. Smith and B. Gopal" ,TITLE = "WebGlimpse: Combining Browsing and Searching" ,BOOKTITLE = "Proceedings of 1997 Usenix Technical Conference" ,YEAR = "1997" ,entered-by = "Junghoo Cho" ,abstract = {The two paradigms of searching and browsing are currently almost always used separately. One can either look at the library card catalog, or browse the shelves; one can either search large WWW sites (or the whole web), or browse page by page. In this paper we describe a software tool we developed, called WebGlimpse, that combines the two paradigms. It allows the search to be limited to a neighborhood of the current document. WebGlimpse automatically analyzes collections of web pages and computes those neighborhoods (at indexing time). With WebGlimpse users can browse at will, using the same pages; they can also jump from each page, through a search to close-by pages related to their needs. } } @ARTICLE{BEBR92 ,AUTHOR = "N.J. Belkin and W. Bruce Croft" ,TITLE = "Information filtering and information retrieval: two sides of same coin?" ,JOURNAL = cacm ,YEAR = "1992" ,month = "December" ,volume = "35" ,number = "12" ,pages = "29-38" ,entered-by = "Junghoo Cho" ,abstract = {A comparison is made between information retrieval and information filtering. The authors determine that information filtering is a well defined process. By examining its foundations and comparing it to the foundations of the IR enterprise, the authors find there is very little difference between filtering and retrieval at an abstract level. They conclude that the two enterprises have the same goal; namely they are both concerned with getting information to people who need it. However, the authors emphasize that IR research has ignored some aspects of the general problem which both IR and information filtering address, and that these aspects are precisely those which especially relevant to the specific contexts of filtering. } } @INPROCEEDINGS{CRB98 ,AUTHOR = "M. Chalmers and K. Rodden and D. Brodbeck" ,TITLE = "The order of things: activity-centered information access" ,BOOKTITLE = "Proceedings of the 7th World Wide Web Conference" ,YEAR = "1998" ,entered-by = "Junghoo Cho" ,abstract = {This paper focuses on the representation and access of Web-based information, and how to make such a representation adapt to the activities or interests of individuals within a community of users. The heterogeneous mix of information on the Web restricts the coverage of traditional indexing techniques and so limits the power of search engines. In contrast to traditional methods, and in a way that extends collavotaive filtering approaches, the path model centers representation on usage histories rather than content analysis. By putting activity at the center of representation and not the periphery, the path model concentrates on the reader not the author and the brower not the site. We describe metrics of similarity based on the path model, and their application in a URL recommender tool and in visualising sets of URLs. } } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% % % Crawling % @INPROCEEDINGS{HJMPSU98 ,AUTHOR = "M. Hersovici and M. Jacovi and Y. Maarek and D. Pelleg and M. Shtalhaim and S. Ur" ,TITLE = "The shark-search algorithm - An application: tailored Web site mapping" ,BOOKTITLE = "Proceedings of the 7th World Wide Web Conference" ,YEAR = "1998" ,entered-by = "Junghoo Cho" ,abstract = {This paper introduces the shark search algorithm, a refined version of the first dynamic Web search lgorithms, the fish search. The shark-search has been embodied into a dynamic Web site mapping that enables users to tailor Web maps to their interests. Preliminary experiments show significant improvement over the original fish-search algorithm.} } @INPROCEEDINGS{MIBH98 ,AUTHOR = "R. Miller and K. Bharat" ,TITLE = "SPHINX: a framework for creating personal site-specific Web crawlers" ,BOOKTITLE = "Proceedings of the 7th World Wide Web Conference" ,YEAR = "1998" ,entered-by = "Junghoo Cho" ,abstract = {Crawlers, also called robots and spiders, are programs that browse the World Wide Web autonomously. This paper describes SPHINX, a Java toolkit and interactive development environment for Web crawlers. Unlike other crawler development systems, SPHINX is geared towards developming crawlers that are Web-site specific, personally customized, and relocatable. SPHINX allows site-specific crawling rules to be encapsulated and reused in content analyzers, known as classifiers. Personal crawling tasks can be performed in the Crawler Workbench, an interactive environment for crawler development and testing. For efficiency, relocatable crawlers developed using SPHINX can be uploaded and executed on a remote Web server.} } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% % % Adaptive WebSite: University of Washington % @INPROCEEDINGS{PEET97 ,AUTHOR = "M. Perkowitz and O. Etzioni" ,TITLE = "Adaptive Web Sites: an AI Challenge" ,BOOKTITLE = "Fifteenth International Joint Conference on Intelligence" ,YEAR = "1997" ,entered-by = "Junghoo Cho" ,abstract = {The creation of a complex web site is a thorny problem in user interface design. First, differnt visitors have distinct goals. Second, even a single visitor may have different needs at different times. Much of the information at the site may also be dynamic or time-dependent. Third, as the site grows and evolves, its original design may no longer be appropriate. Finally, a site may be designed for a particular purpose but used in unexpected ways. Web servers record data about user interactions and accumulate this data over time. We believe that AI techniques can be used to examine user access logs in order to automatically improve the site. We challenge the AI community to create adaptive web sites: sites that automatically improve their organization and presentation based on user access data. Several unrelated research projects in plan recognition, machine learning, knowledge representation, and user modeling have begun to explore aspects of this problem. We hope that posing this challenge explicitly will bring these projects together and stimulate fundamental AI research. Success would have a broad and highly visible impact on the web and the AI community. } } @INPROCEEDINGS{PEET98 ,AUTHOR = "M. Perkowitz and O. Etzioni" ,TITLE = "Adaptive Web Sites: Automatically Synthesizing Web Pages" ,BOOKTITLE = "Fifteenth National Conference on Artificial Intelligence" ,YEAR = "1998" ,entered-by = "Junghoo Cho" ,abstract = {The creation of a complex web site is a thorny problem user interface design. In IJCAI '97, we challenged the AI community to address this problem by creating adaptive web sites: sites that automatically improve their organization and presentation by min- ing visitor access data collected in Web server logs. In this paper we introduce our own approach to this broad challenge. Specifically, we investigate the problem of index page synthesis --- the automatic creation of pages that facilitate a visitor's navigation of a Web site. First, we formalize this problem as a clustering problem and introduce a novel approach to clustering, which we call cluster mining: Instead of attempting to partition the entire data space into disjoint clusters, we search for a small number of cohesive (and possibly overlapping) clusters. Next, we present PageGather, a cluster mining algorithm that takes Web server logs as input and outputs the contents of candidate index pages. Finally, we show experimentally that Page-Gather is both faster (by a factor of three) and more effective than traditional clustering algorithms on this task. Our experiment relies on access logs collected over a month from an actual web site. } } @INPROCEEDINGS{MOSH94a ,AUTHOR = "M. Morita and Y. Shinoda" ,TITLE = "Information filtering based on user behavior analysis and best match text retrieval" ,BOOKTITLE = sigir94 ,YEAR = "1994" ,entered-by = "Junghoo Cho" } @InProceedings{lai98, author = "Kevin Lai and Mema Roussopoulos and Diane Tang and Xinhua Zhao and Mary Baker", title = "Experiences with a Mobile Testbed", booktitle = "Proceedings of The Second International Conference on Worldwide Computing and its Applications (WWCA'98)", year = 1998, month = "Mar", key = "Mobile computing; Mobile networking", entered-by = "Henry Berg" } @InProceedings{poge97, author = "E. Poger and M. Baker", title = "Secure Public Internet Access Handler (SPINACH)", booktitle = "Proceedings of the USENIX Symposium on Internet Technologies and Systems", year = 1997, month = "Dec", key = "Mobile computing; Mobile networking", entered-by = "Henry Berg" } @InProceedings{ches96, author = "S. Cheshire and M. Baker", title = "Internet Mobility 4x4", booktitle = "Proceedings of the ACM SIGCOMM'96 Conference", year = 1996, month = "Aug", key = "Mobile computing; Mobile networking", entered-by = "Henry Berg" } @InProceedings{bake96, author = "M. Baker and X. Zhao and S. Cheshire and J. Stone", title = "Supporting Mobility in MosquitoNet", booktitle = "Proceedings of the 1996 USENIX Conference", year = 1996, month = "Jan", key = "Mobile computing; Mobile networking", entered-by = "Henry Berg" } @Article{ches96a, author = "S. Cheshire and M. Baker", title = "A Wireless Network in MosquitoNet", journal = "IEEE Micro", year = 1996, month = "Feb", key = "Mobile computing; Mobile networking", entered-by = "Henry Berg" } @InProceedings{bake94, author = "M. Baker", title = "Changing Communication Environments in MosquitoNet", booktitle = "Proceedings of the IEEE Workshop on Mobile Computing Systems and Applications", year = 1994, month = "Dec", key = "Mobile computing; Mobile networking", entered-by = "Henry Berg" } @MANUAL{trade97 ,TITLE = "ITU/ISO ODP Trading Function" ,organization = "ISO/IEC" ,note = "ISO/IEC IS 13235-1, ITU/T Draft Rec X950-1" ,year = "1997" ,entered-by = "Andreas Paepcke" ,keywords = "trading service" ,abstract = {~} } @techreport{ansaManual, author = "J. P. Deschrevel", title = "The ANSA Model for Trading and Federation", institution = "APM, Cambridge", year = 1989, number = "APM.1005.01", } @article{odpTrader, author = "M. Bearman", title = "ODP-Trader", journal = "Open Distributed Processing", volume = 2, pages = "19 - 33", editedby = "J. de Meer and B. Mahr and S. Storp", publisher = "North-Holland", year = 1994, } @Article{fox96a, author = "Armando Fox and Steven D. Gribble and Eric A. Brewer and Elan Amir", title = "Adapting to network and client variability via on-demand dynamic distillation", key = "client-server systems; data compression; Internet; performance evaluation; client variability; on-demand dynamic distillation; Internet; smart cellular phones; handheld wireless devices; Internet clients; hardware resources; software sophistication; connectivity; server support; client variation; on-demand datatype-specific lossy compression; semantically typed data; proxy architecture; application-level management; display output; end-to-end performance; low-end clients", journal = "SIGPLAN Not. (USA), SIGPLAN Notices", year = 1996, volume = 31, number = 9, pages = "160-70", month = "Sep", note = "Also Seventh Intl. Conf. on Arch. Support for Prog. Lang. and Oper. Sys. (ASPLOS-VII)", abstract = {The explosive growth of the Internet and the proliferation of smart cellular phones and handheld wireless devices is widening an already large gap between Internet clients. Clients vary in their hardware resources, software sophistication, and quality of connectivity, yet server support for client variation ranges from relatively poor to none at all. In this paper we introduce some design principles that we believe are fundamental to providing "meaningful" Internet access for the entire range of clients. In particular, we show how to perform on-demand datatype-specific lossy compression on semantically typed data, tailoring content to the specific constraints of the client. We instantiate our design principles in a proxy architecture that further exploits typed data to enable application-level management of scarce network resources. Our proxy architecture generalizes previous work addressing all three aspects of client variation by applying well-understood techniques in a novel way, resulting in quantitatively better end-to-end performance, higher quality display output, and new capabilities for low-end clients.}, entered-by = "Henry Berg" } @InProceedings{fox97, author = "A. Fox and S. D. Gribble and Y. Chawathe and A. S. Polite and A. Huang and B. Ling and E. A. Brewer", title = "Orthogonal extensions to the WWW user interface using client-side technologies", key = "data compression; hypermedia; image coding; Internet; object-oriented languages; page description languages; user interfaces; WWW user interface; orthogonal extensions; client-side technology; intelligent services; user control; Web browsing; TranSend service; lossy compression; inline images; dialup Web access; preferences profile; HTML; Java; JavaScript; World Wide Web interface; Internet", pages = "83-4", booktitle = "Proceedings of the ACM Symposium on User Interface Software and Technology. 10th Annual Symposium. UIST '97", year = 1997, month = "Oct", abstract = "We describe our experience implementing orthogonal extensions to the existing WWW user interface, to support user control of intelligent services. Our extensions are orthogonal in that they provide an interface to a service, which complements the Web browsing experience but is independent of the content of any particular site. We base our experiments on the TranSend service at UC Berkeley, which performs lossy compression on inline images to accelerate dialup Web access for a community of 25,000 subscribers. The service keeps a separate preferences profile for each user, which allows each user to vary the aggressiveness of lossy compression, selectively turn off the service for certain pages, and select the type of interface provided for refinement of degraded (lossily compressed) content. We are exploring three technologies for implementing the TranSend service interface: HTML decoration, Java and JavaScript.", entered-by = "Henry Berg" } @Article{fox96b, author = "Armando Fox and Eric A. Brewer", title = "Reducing WWW latency and bandwidth requirements by real-time distillation", journal = "Comput. Netw. ISDN Syst. (Netherlands), Computer Networks and ISDN Systems", year = 1996, volume = 28, number = "7-11", pages = "1445-56", month = "May", note = "cache storage; client-server systems; computer communications software; data compression; Internet; network servers; real-time systems; network latency; bandwidth requirements; real-time distillation; Pythia proxy mechanism; World Wide Web; real-time refinement; statistical models; metered cellular phone service; transcoding; client-side rendering; data representation; client display constraints; content optimization; PPP; Point-to-Point Protocol; image loading; added value", abstract = "The Pythia proxy mechanism provides three important orthogonal benefits to World Wide Web (WWW) clients. (1) Real-time distillation and refinement, guided by statistical models, allow the user to bound latency and exercise explicit control over bandwidth that may be scarce and expensive (e.g. a metered cellular phone service). (2) Transcoding to a representation understood directly by the client system may improve rendering on the client or result in a representation that can be transmitted more efficiently. (3) Knowledge of client display constraints allows content to be optimized for rendering on the client. Users have commented that even the prototype version of Pythia provides a qualitative increase of about 5 times when surfing the World Wide Web over PPP (Point-to-Point Protocol) with a 14.4 kbit/s modem. These are the same users that previously turned image loading off completely in order to make surfing bearable. With the continued growth of the WWW, the benefits afforded by proxied services like Pythia will represent increasingly significant added value to end users and content providers alike. Pythia is the first fruit of a comprehensive research agenda aimed at implementing and deploying such services.", entered-by = "Henry Berg" } @Article{nara96, author = "S. Narayanaswamy and S. Seshan and E. Amir and E. Brewer and R. W. Brodersen and F. Burghardt and A. Burstein and Yuan-Chi Chang and A. Fox and J. M. Gilbert and R. Han and R. H. Katz and A. C. Long and D. G. Messerschmitt and J. M. Rabaey", title = "A low-power, lightweight unit to provide ubiquitous information access application and network support for InfoPad", journal = "IEEE Personal Communications", year = 1996, volume = 3, number = 2, pages = "4-17", month = "Apr", key = "data communication; indoor radio; Internet; land mobile radio; multimedia communication; network servers; portable computers; speech recognition; telecommunication terminals; user interfaces; information access application; network support; network servers; computer systems; multimedia Internet services; portable computing; wireless data communications; InfoPad project; lightweight wireless multimedia terminal; low-power lightweight unit; InfoPad system; high bandwidth connectivity; portability; user interface; design; software network; application services; InfoPad terminal; speech recognizers; portable terminal; servers; routing; handoff; indoor environment; InfoNet system", abstract = "Some of the most important trends in computer systems are the emerging use of multimedia Internet services, the popularity of portable computing, and the development of wireless data communications. The primary goal of the InfoPad project is to combine these trends to create a system that provides ubiquitous information access. The system is built around a low-power, lightweight wireless multimedia terminal that operates in indoor environments and supports a high density of users. The InfoPad system uses a number of innovative techniques to provide the high-bandwidth connectivity, portability, and user interface needed for this environment. The article describes the design, implementation, and evaluation of the software network and application services that support the InfoPad terminal. Special applications, type servers, and recognizers are developed for the InfoPad system. This software is designed to take advantage of the multimedia capabilities of the portable terminal and the additional computational resources available on the servers. The InfoNet system provides low-latency, high bandwidth connectivity between the computation and the portable terminal. It also provides the routing and handoff support that allows users to roam freely. The performance measurements of the system show that this design is a viable alternative, especially in the indoor environment.", entered-by = "Henry Berg" } @ARTICLE{mill98 ,AUTHOR = "Eric Miller" ,TITLE = "An Introduction to the Resource Description Framework" ,JOURNAL = "D-Lib Magazine" ,YEAR = "1998" ,month = "May" ,note = "http://www.dlib.org/dlib/may98/miller/05miller.html" ,entered-by = "Andreas Paepcke" ,keywords = "RDF, resource description framework, metadata, XML" ,abstract = {~} } @MANUAL{rdf98 ,TITLE = "Resource Description Framework (RDF) Model and Syntax Specification" ,INSTITUTION = "World-Wide Web Consortium" ,YEAR = "1998" ,number = "WD-rdf-syntax-19980819" ,note = "Available at http://www.w3.org/TR/WD-rdf-syntax/" ,links = "(title:www:http://www.w3.org/TR/WD-rdf-syntax/)" ,entered-by = "Andreas Paepcke" ,keywords = "RDF, Resource Description Framework" ,abstract = {~} } @ARTICLE{paep98a ,AUTHOR = "Andreas Paepcke and Michelle Baldonado and Chen-Chuan K. Chang and Steve Cousins and Hector Garcia-Molina " ,TITLE = "Using distributed objects to build the Stanford digital library Infobus" ,JOURNAL = ieeecomp ,YEAR = "1999" ,volume = 32 ,number = 2 ,pages = "80--87" ,month = "February" ,note = "Similar version available at http://dbpubs.stanford.edu/pub/2000-50. Title = Building the InfoBus" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-50)" ,entered-by = "Andreas Paepcke" ,keywords = "InfoBus, digital library, CORBA, distributed objects, USMARC, query processing, interoperability, heterogeneous systems, metadata, state management" ,abstract = {We review selected technical challenges addressed in our digital library project. Our InfoBus, a CORBA-based distributed object infrastructure, unifies access to heterogeneous document collections and information processing services. We organize search access using a protocol (DLIOP) that is tailored for use with distributed objects. A metadata architecture supports novel user interfaces and query translation facilities. We briefly explain these components and then describe how technology choices such as distributed objects, commercial cataloguing schemes and Java, helped and hindered our progress. We also describe the evolution of our design tradeoffs.} } @INPROCEEDINGS{hear95 ,AUTHOR = "Marti A. Hearst" ,TITLE = "TileBars: Visualization of Term Distribution Information in Full Text Information Access" ,BOOKTITLE = chi95 ,YEAR = "1995" ,entered-by = "Andreas Paepcke" ,keywords = "TileBars" ,abstract = {The field of information retrieval has traditionally focused on textbases consisting of titles and abstracts. As a consequence, many underlying assumptions must be altered for retrieval from full-length text collections. This paper argues for making use of text structure when retrieving from full text documents, and presents a visualization paradigm, called TileBars, that demonstrates the usefulness of explicit term distribution information in Boolean-type queries. TileBars simultaneously and compactly indicate relative document length, query term frequency, and query term distribution. The patterns in a column of TileBars can be quickly scanned and deciphered, aiding users in making judgments about the potential relevance of the retrieved documents. } } @INPROCEEDINGS{stai97 ,AUTHOR = "Mark A. Stairmand" ,TITLE = "Textual Content Analysis for Information Retrieval" ,BOOKTITLE = sigir97 ,YEAR = "1997" ,entered-by = "Andreas Paepcke" ,keywords = "WordNet, semantics-based retrieval" ,abstract = {Shows how WordNet-based search facility doesn't work for text segmentation and word disambiguation, but that it does work for improved indexing} } @INPROCEEDINGS{cutt92 ,AUTHOR = "Douglass R. Cutting and Jan O. Pedersen and David Karger and John W. Tukey" ,TITLE = "Scatter/Gather: A Cluster-based Approach to Browsing Large Document Collections" ,BOOKTITLE = sigir92 ,YEAR = "1992" ,pages = "318-329" ,entered-by = "Andreas Paepcke" ,keywords = "Scatter/Gather" ,abstract = {~} } @INPROCEEDINGS{cutt93 ,AUTHOR = "Douglass R. Cutting and David Karger and Jan Pedersen" ,TITLE = "Constant interaction-time Scatter/Gather browsing of very large document collections" ,BOOKTITLE = sigir93 ,YEAR = "1993" ,pages = "126-135" ,entered-by = "Andreas Paepcke" ,keywords = "Scatter/Gather" ,abstract = {~} } @INPROCEEDINGS{kess97 ,AUTHOR = "Brett Kessler and Geoffrey Nunberg and Hinrich Schuetze" ,TITLE = "Automatic Detection of Text Genre" ,BOOKTITLE = "Proceedings ACL/EACL" ,YEAR = "1997" ,links = "(title:www:http://xxx.lanl.gov/abs/cmp-lg/?9707002)" ,entered-by = "Andreas Paepcke" ,keywords = "genre detection, automatic text complexity analysis, value filtering" ,abstract = {Describes experiment where they detected genre just from surface features, not from tags marking structures. They show that they can do at least as well with this low-overhead approach as others can with tagging. They also detect level of sophistication} } @INPROCEEDINGS{cho98a ,AUTHOR = "Junghoo Cho and Narayanan Shivakumar and Hector Garcia-Molina" ,TITLE = "Computing Document Clusters on the Web" ,BOOKTITLE = sigmod00 ,YEAR = "1998" ,entered-by = "Andreas Paepcke" ,keywords = "SCAM, mirror site detection, value filtering, crawling" ,abstract = {They crawl the Web and automatically find out which sites completely or partially mirror each other.} } @INPROCEEDINGS{mack89 ,AUTHOR = "Wendy E. Mackay and Thomas W. Malone and Kevin Crowston and Ramana Rao and David Rosenblitt and Stuart K. Card" ,TITLE = "How Do Experienced Information Lens Users Use Rules?" ,BOOKTITLE = chi89 ,YEAR = "1989" ,entered-by = "Andreas Paepcke" ,found-in = "Paepcke's files" ,keywords = "information lens, mail agents, filters" ,abstract = {Study of 13 users to show that rules work for mail presorting.} } @ARTICLE{malo87 ,AUTHOR = "Thomas W. Malone and Kenneth R. Grant and Kum-Yew Lai and Ramana Rao and David Rosenblitt" ,TITLE = "Semistructured Messages are Surprisingly Useful for Computer-Supported Coordination" ,JOURNAL = tois ,YEAR = "1987" ,month = "April" ,volume = "5" ,number = "2" ,pages = "115-131" ,entered-by = "Andreas Paepcke" ,found-in = "db library" ,keywords = "Information Lens, semi-structured data, filtering, email" ,abstract = {Show how they Information Lens lets users write rules about email. Explains that semi-structured data is special} } @ARTICLE{poll88 ,AUTHOR = "Stephen Pollock" ,TITLE = "A Rule-Based Message Filtering System" ,JOURNAL = tranos ,YEAR = "1988" ,month = "July" ,volume = "6" ,number = "3" ,entered-by = "Andreas Paepcke" ,found-in = "Paepcke's files" ,status = "skimmed" ,keywords = "mail agents, ISCREEN, filters" ,abstract = {You write rules and the system filters your mail.} } @phdthesis{sahami-thesis, author={Mehran Sahami}, title={Using Machine Learning to Improve Information Access}, year=1998, address={Computer Science Department}, school={Stanford University}} @INPROCEEDINGS{paep98b ,AUTHOR = "Andreas Paepcke and Hector Garcia-Molina and Gerard Rodriquez" ,TITLE = "Collaborative Value Filtering on the Web. KSS" ,BOOKTITLE = www98 ,YEAR = "1998" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-47)" ,entered-by = "Andreas Paepcke" ,keywords = "KSS, value filtering" ,abstract = {Additional citation info: Computer and ISDN Systems (1998). Volume 30, Numbers 1-7, April 1998} } @ARTICLE{paep98c ,AUTHOR = "Andreas Paepcke and Hector Garcia-Molina and Gerard Rodriguez and Junghoo Cho" ,TITLE = "Beyond Document Similarity: Understanding Value-Based Search and Browsing Technologies" ,JOURNAL = "SIGMOD Records" ,YEAR = "2000" ,month = "March" ,volume = "29" ,number = "1" ,pages = "~" ,note = "Available at http://dbpubs.stanford.edu/pub/2000-5" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-5)" ,entered-by = "Andreas Paepcke" ,keywords = "value filtering" ,abstract = {High volumes of diverse documents on the Web are overwhelming search and ranking technologies that are based on document similarity measures. The increase of multimedia data within documents sharply exacerbates the shortcomings of these approaches. Recently, research prototypes and commercial experiments have added techniques that augment similarity-based search and ranking. These techniques rely on judgments about the value of documents. Judgments are obtained directly from users, are derived by conjecture based on observations of user behavior, or are surmised from analyses of documents and collections. All these systems have been pursued independently, and no common understanding of the underlying processes has been presented. We survey existing value-based approaches, develop a reference architecture that helps compare the approaches, and categorize the constituent algorithms. We explain the options for collecting value metadata, and for using that metadata to improve search, ranking of results, and the enhancement of information browsing. Based on our survey and analysis, we then point to several open problems.} } @BOOK{filt92 ,AUTHOR = "Shoshana Loeb and Douglas Terry" ,TITLE = "Information Filtering" ,PUBLISHER = "Communications of the ACM" ,YEAR = "1992" ,month = "December" ,entered-by = "Andreas Paepcke" ,keywords = "value filtering" ,abstract = {This entry is here to allow citing of this CACM issue as a whole} } @BOOK{reco97 ,AUTHOR = "Paul Resnick and Hal R. Varian" ,TITLE = "Recommender Systems" ,PUBLISHER = "Communications of the ACM" ,YEAR = "1997" ,month = "March" ,entered-by = "Andreas Paepcke" ,keywords = "value filtering" ,abstract = {This entry is here to allow citing of this CACM issue as a whole} } @INPROCEEDINGS{brin98b ,AUTHOR = "Sergey Brin" ,TITLE = "Extracting Patterns and Relations from the World Wide Web" ,BOOKTITLE = "WebDB Workshop at 6th International Conference on Extending Database Technology, EDBT'98" ,YEAR = "1998" ,note = "Available at http://www-db.stanford.edu/~sergey/extract.ps" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1999-65)" ,entered-by = "Andreas Paepcke" ,keywords = "value filtering, pattern derivation, data mining, genre detection" ,abstract = {Seed a search with examples of a pattern, such as citations to books. Let the engine run over Web pages and learn. Get back more books.} } @INPROCEEDINGS{bran99 ,AUTHOR = "Onn Brandman and Hector Garcia-Molina and Andreas Paepcke" ,TITLE = "Where Have You Been? A Comparison of Three Web Tracking Technologies" ,BOOKTITLE = "Submitted for publication" ,YEAR = "1999" ,note = "Available at http://dbpubs.stanford.edu/pub/1999-61" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1999-61)" ,entered-by = "Andreas Paepcke" ,keywords = "Web tracking, value filtering" ,abstract = {Web searching and browsing can be improved if browsers and search engines know which pages users frequently visit. 'Web tracking' is the process of gathering that information. The goal for Web tracking is to obtain a database describing Web page download times and users' page traversal patterns. The database can then be used for data mining or for suggesting popular or relevant pages to other users. We implemented three Web tracking systems, and compared their performance. In the first system, rather than connecting directly to Web sites, a client issues URL requests to a proxy. The proxy connects to the remote server and returns the data to the client, keeping a log of all transactions. The second system uses "sniffers" to log all HTTP traffic on a subnet. The third system periodically collects browser log files and sends them to a central repository for processing. Each of the systems differs in its advantages and pitfalls. We present a comparison of these techniques.} } @MISC{squi99 ,title = "Squid Internet Object Cache" ,year = "1999" ,entered-by = "Onn Brandman" ,keywords = "Web proxy, web cache, access tracking, value filtering" ,abstract = {Freeware Web proxy that can provide caching services} ,links="(title:www:http://squid.nlanr.net/Squid/)" } @MISC{dirh99 ,title = "Direct Hit" ,year = "1999" ,entered-by = "Onn Brandman" ,keywords = "Web tracking, value filtering" ,abstract = {Company that provides search tracking services} ,links="(title:www:http://www.directhit.com)" } @BOOK{yate99 ,AUTHOR = "Ricardo Baeza-Yates and Berthier Ribeiro-Neto" ,TITLE = "Modern Information Retrieval" ,PUBLISHER = "Addison-Wesley-Longman" ,YEAR = "1999" ,month = "May" ,entered-by = "Andreas Paepcke" ,abstract = {The chapters of the book are: Introduction Modeling Retrieval Evaluation Query Languages (with Gonzalo Navarro) Query Operations Text and Multimedia Languages and Properties Text Operations (with Nivio Ziviani) Indexing and Searching (with Gonzalo Navarro) Parallel and Distributed IR (by Eric Brown) User Interfaces and Visualization (by Marti Hearst) Multimedia IR: Models and Languages (by Elisa Bertino, Barbara Catania and Elena Ferrari) Multimedia IR: Indexing and Searching (by Christos Faloutsos) Searching the Web Libraries and Bibliographic Systems (by Edie Rasmussen) Digital Libraries (by Edward Fox and Ohm Sornil) Appendix: Porter's Algorithm Glossary References (more than 800) Index More information can be found in: http://www.sims.berkeley.edu/~hearst/irbook } } @article{scha94 ,AUTHOR = "Linda Schamber" ,TITLE = "Relevance and Information Behavior" ,JOURNAL = "Annual Review of Information Science and Technology (ARIST)" ,YEAR = "1994" ,volume = "29" ,pages = "3--48" ,editor = "Martha E. Williams" ,publisher = "American Society for Information Science (ASIS)" ,entered-by = "Andreas Paepcke" ,keywords = "relevance, information utility, information retrieval" ,abstract = {This is a long survey of what people have said/thought about information relevance. (See also Mizz97)} } @ARTICLE{mizz97 ,AUTHOR = "Stefano Mizzaro" ,TITLE = "Relevance: The Whole History" ,JOURNAL = jasis ,YEAR = "1997" ,volume = "48" ,number = "9" ,pages = "810--832" ,entered-by = "Andreas Paepcke" ,keywords = "relevance, information utility, information retrieval" ,abstract = {Historical roundup of thoughts on relevance. Nicely written. Covers three eras: 17th century-1958; 1958-1976; 1977-1997; Lists the essentials of about 160 papers, summarizing their respective contributions for several aspects of relevance.} } @INPROCEEDINGS{halp99a ,AUTHOR = "Joseph Y. Halpern and Carl Lagoze" ,TITLE = "The Computing Research Repository: Promoting the Rapid Dissemination and Archiving of Computer Science Research" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,abstract = {We describe the Computing Research Repository (CoRR), a new electronic archive for rapid dissemination and archiving of computer science research results. CoRR was initiated in September 1998 through the cooperation of ACM, LANL (Los Alamos National Laboratory) e-Print archive, and NCSTRL (Networked Computer Science Technical Reference Library. Through its implementation of the Dienst protocol, CoRR combines the open and extensible architecture of NCSTRL with the reliable access and well-established management practices of the LANL XXX e-Print repository. This architecture will allow integration with other e-Print archives and provides a foundation for a future broad-based scholarly digital library. We describe the decisions that were made in creating CoRR, the architecture of the CoRR/NCSTRL interoperation, and issues that have arisen during the operation of CoRR.} } @INPROCEEDINGS{dunn99a ,AUTHOR = "Jon W. Dunn and Costance A. Mayer" ,TITLE = "VARIATIONS: A Digital Music Library System at Indiana University" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "music libraries, digital audio" ,abstract = {The field of music provides an interesting context for the development of digital library systems due to the variety of information formats used by music students and scholars. The VARIATIONS digital library project at Indiana University currently delivers online access to sound recordings from the collections of IU's William and Gayle Cook Music Library and is developing access to musical score images and other formats. This paper covers the motivations for the creation of VARIATIONS, an overview of its operation and implementation, user reactions to the system, and future plans for development.} } @INPROCEEDINGS{phan99a ,AUTHOR = "Constantinos Phanouriou and Neill A. Kipp and Ohm Sornil and Paul Mather and Edward A. Fox" ,TITLE = "A Digital Library for Authors: Recent Progress of the Networked Digital Library of Theses and Dissertations" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "dissertations, thesis" ,abstract = {The Networked Digital Library of Theses and Dissertations (NDLTD) is more than an online collection of Electronic Theses and Dissertations (ETDs). It is a scalable project that has impact on thousands of graduate students in many countries as well as diverse researchers worldwide. By May 1999 it had 59 official members rep resenting 13 countries and integrated some of the world's newest research works, including ETD collections at Virginia Tech and West Virginia University, where ETD submission is now required. The number of accesses to the Virginia Tech collection has grown by more than half in the last year. NDLTD is committed to authors, aiming to improve graduate education for the over 100,000 students that prepare a thesis or dissertation each year. It encourages them to be more expressive by facilitating incorporation of multimedia components into their theses. NDLTD activities include: applying automation methods to simplify submission of ETDs over the WWW; specifying the application of the Dublin Core to guarantee that metadata can satisfy needs of search- ing and browsing; selecting open standards and procedures to facilitate interoperability and preservation; and demonstrating a variety of interfaces, both 2D and 3D, along with exploring their usability.} } @INPROCEEDINGS{chen99a ,AUTHOR = "Yuan Chen and Jan Edler and Andrew Goldberg and Allan Gottlieb and Sumeet Sobti and Peter Yianilos" ,TITLE = "A Prototype Implementation of Archival Intermemory" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "archival storage, distributed redundant databases" ,abstract = {An Archival Intermemory solves the problem of highly survivable digital data storage in the spirit of the Internet. In this paper we describe a prototype implementation of Intermemory, including an overall system architecture and implementations of key system components. The result is a working Intermemory that tolerates up to 17 simultaneous node failures, and includes a Web gateway for browser-based access to data. Our work demonstrates the basic feasibility of Intermemory and represents significant progress towards a deployable system.} } @INPROCEEDINGS{chun99a ,AUTHOR = "Y-Ming Chung and Qin He and Kevin Powell and Bruce Schatz" ,TITLE = "Semantic Indexing for a Complete Subject Discipline" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "semantic indexing, concept space" ,abstract = {As part of the Illinois Digital Library Initiative (DLI) project we developed "scalable semantics" technologies. These statistical techniques enabled us to index large collections for deeper search than word matching. Through the auspices of the DARPA Information Management program, we are developing an integrated analysis environment, the Interspace Prototype, that uses "semantic indexing" as the foundation for supporting concept navigation. These semantic indexes record the contextual correlation of noun phrases, and are computed generically, independent of subject domain. Using this technology, we were able to compute semantic indexes for a subject discipline. In particular, in the summer of 1998, we computed concept spaces for 9.3M MEDLINE bibliographic records from the National Library of Medicine (NLM) which extensively covered the biomedical literature for the period from 1966 to 1997. In this experiment, we first partitioned the collection into smaller collections (repositories) by subject, extracted noun phrases from titles and abstracts, then performed semantic indexing on these subcollections by creating a concept space for each repository. The computation required 2 days on a 128-node SGI/CRAY Origin 2000 at the National Center for Supercomputer Ap- plications (NCSA). This experiment demonstrated the feasibility of scalable semantics techniques for large collections. With the rapid increase in computing power, we believe this indexing technology will shortly be feasible on personal computers.} } @INPROCEEDINGS{doli99a ,AUTHOR = "R. Dolin and D. Agrawal and A. El Abbadi" ,TITLE = "Scalable Collection Summarization and Selection" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "resource discovery" ,abstract = {Information retrieval over the Internet increasingly requires the filtering of thousands of information sources. As the number and variety of sources increases, new ways of automatically summarizing, discovering, and selecting sources relevant to a user's query are needed. Pharos is a highly scalable distributed architecture for locating heterogeneous information sources. Its design is hierarchical, thus allowing it to scale well as the number of information sources increases. We demonstrate the feasibility of the Pharos architecture using 2500 Usenet newsgroups as separate collections. Each newsgroup is summarized via automated Library of Congress classification. We show that using Pharos as an intermediate retrieval mechanism provides acceptable accuracy of source selection compared to selecting sources using complete classification information, while maintaining good scalability. This implies that hierarchical distributed metadata and automated classification are potentially useful paradigms to address scalability problems in large-scale distributed information retrieval applications.} } @INPROCEEDINGS{cres99a ,AUTHOR = "Fabio Crestani" ,TITLE = "Vocal Access to a Newspaper Archive: Design Issues and Preliminary Investigations" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,abstract = {This paper presents the design and the current prototype implementation of an interactive vocal Information Retrieval system that can be used to access articles of a large news paper archive using a telephone. The results of preliminary investigation into the feasibility of such a system are also presented.} } @INPROCEEDINGS{hu99a ,AUTHOR = "Michael J. Hu and Ye Jian" ,TITLE = "Multimedia Description Framework (MDF) for Content Description of Audio/Video Documents" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "meta-data, content description" ,abstract = {MPEG is undertaking a new initiative to standardize content description of audio and video data/documents. When it is finalized in 2001, MPEG-7 is expected to provide standardized description language and schemes for concise and unambiguous content description of data/documents of complex media types. Meanwhile, other meta-data or description schemes, such as Dublin Core, XML, RDF, etc., are becoming popular in different application domains. In this paper, we propose Multimedia Description Framework (MDF), which is designated to accommodate multiple description (meta-data) schemes, MPEG-7 and non-MPEG-7, into integrated architecture. We will u`se examples to show how MDF description makes use of combined strength of different description schemes to enhance its expression power and flexibility. We conclude the paper with discussion of using MDF description of MPEG-7 Content Set to search/retrieve required audio and video documents from the set utilizing an MDF prototype system we have implemented.} } @INPROCEEDINGS{mars99a ,AUTHOR = "Catherine C. Marshall and Morgan N. Price and Gene Golovchinsky and Bill N. Schilit" ,TITLE = "Introducing a digital library reading appliance into a reading group" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "e-book, paper document metaphor" ,abstract = {How will we read digital library materials? This paper describes the reading practices of an on-going reading group, and how these practices changed when we introduced XLibris, a digital library reading appliance that uses a pen tablet computer to provide a paper-like interface. We interviewed group members about their reading practices, observed their meetings. and analyzed their annotations. both when they read a paper document and when they read using XLibris: We use these data to characterize their analytic reading, reference use, and annotation practices. We also describe the use of the Reader's Notebook, a list of clippings that XLibris computes from a reader's annotations. Implications for digital libraries stem from our findings on reading and mobility. the complexity of analytic reading, the social nature of reference following. and the unselfconscious nature of readers' annotations.} } @INPROCEEDINGS{ding99a ,AUTHOR = "Wei Ding and Gary Marchionini and Dagobert Soergel" ,TITLE = "Multimodal Surrogates for Video Browsing" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "abstracting methods" ,abstract = {Three types of video surrogates - visual (keyframes), verbal (keywords/phrases), and visual and verbal - were designed and studied in a qualitative investigation of user cognitive processes. The results favor the combined surrogates in which verbal information and images reinforce each other, lead to better comprehension, and may actually require less processing time, The results also highlight image features users found most helpful. These findings will inform the interface design and video representation for video retrieval and browsing.} } @INPROCEEDINGS{bish99a ,AUTHOR = "Ann Peterson Bishop" ,TITLE = "Making Digital Libraries Go: Comparing Use Across Genres" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "user studies" ,abstract = {A new federal initiative called Information Technology for the Twenty-First Century (IT2) recognizes the need to bridge research across domains in or&r to bring computing benefits to society at large. One implication for digital library (DL) research is that we should start looking at projects that span the spectrum from basic computer science to the implementation of working systems and consider links among findings on information system use from a variety of arenas in life. In this paper, I integrate findings from my research on people's encounters with DLs in two different arenas: academia and low-income neighborhoods. The point is to see how concepts and conclusions related to use do, in fact, cross these arenas. The paper also aims to help bring results from studies of local community information practices into the realm of DLs, since community networking represents one particular genre and audience that has not yet received a great deal of attention from those engaged in DL research. Beginning with a discussion of DL use as an "assemblage" of infrastructure, norms, knowledge, and practice, the paper explores a number of insights gleaned from user studies associated with two separate research projects: 1) the recently completed University of Illinois Digital Libraries Initiative (DLI) project; and 2) the Community Networking Initiative (CNI) currently in progress under the auspices of the University of Illinois, the Urban League of Champaign County and Prairienet, the community network serving East Central Illinois. Insights about DL use discussed in this paper include: the way in which trivial barriers are magnified until they effectively cut off use on a large scale; the difficulties faced by "outsiders" whose information worlds are impoverished, the primacy of comfort and relevant content in encouraging use; and the importance of informal social networks for providing help related to system use.} } @INPROCEEDINGS{boll99a ,AUTHOR = "Kurt D. Bollacker and Steve Lawrence and C. Lee Giles" ,TITLE = "A System For Automatic Personalized Tracking of Scientific Literature on the Web" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "user profile, citation index" ,abstract = {We introduce a system as part of the CiteSeer digital library project for automatic tracking of scientific literature that is relevant to a user's research interests. Unlike previous systems that use simple keyword matching, CiteSeer is able to track and recommend topically relevant papers even when keyword based query profiles fail. This is made possible through the use of a heterogenous profile to represent user interests. These profiles include several representations, including content based relatedness measures. The CiteSeer tracking system is well integrated into the search and browsing facilities'of CiteSeer, and provides the user with great flexibility in tuning a profile to better match his or her interests. The software for this system is available, and a sample database is online as a public service.} } @INPROCEEDINGS{jone99a ,AUTHOR = "Steve Jones and Gordon Paynter" ,TITLE = "Topic-Based Browsing Within a Digital library Using Keyphrases" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "automated hypertext generation" ,abstract = {Many digital libraries are comprised of documents from disparate sources that are independent of the rest of the collection in which they reside. A user's ability to explore is severely curtailed when each document stands in isolation; there is no way to navigate to other, related, documents, or even to tell if such documents exist. `We describe a method for automatically introducing topic-based links into documents to support browsing in digital libraries. Automatic keyphrase extraction is exploited to identify link anchors, and keyphrase-based similarity measures are used to select and rank destinations. Two implementations are described: one that applies these techniques to existing WWW-based digital library collections using standard HTML, and one that uses a wider range of interface techniques to provide more sophisticated linking capabilities. An evaluation shows that keyphrase-based similarity measures work as well as a popular full-text retrieval system for finding relevant destination documents.} } @INPROCEEDINGS{byrd99a ,AUTHOR = "Donald Byrd" ,TITLE = "A Scrollbar-based Visualization for Document Navigation" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "user interface, user study" ,abstract = {We are interested in questions of improving user control in best- match text-retrieval systems, specifically questions as to whether simple visualizations that nonetheless go beyond the minimal ones generally available can significantly help users. Recently, we have been investigating ways to help users decide-given a set of documents retrieved by a query-which documents and passages are worth closer examination. We built a document viewer incorporating a visualization centered around a novel content-displaying scrollbar and color term highlighting, and studied whether the visualization is helpful to non-expert searchers. Participants' reaction to the visualization was very positive, while the objective results were inconclusive.} } @INPROCEEDINGS{comb99a ,AUTHOR = "Tammara T.A. Combs and Benjamin B. Bederson" ,TITLE = "Does Zooming Improve Image Browsing?" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "zoomable user interfaces" ,abstract = {We describe an image retrieval system we built based on a Zoomable User Interface (ZUI). We also discuss the design, results and analysis of a controlled experiment we performed on the browsing aspects of the system. The experiment resulted in a statistically significant difference in the interaction between number of images (25, 75, 225) and style of browser (2D, ZUI, 3D). The 2D and ZUI browser systems performed equally, and both performed better than the 3D systems. The image browsers tested during the experiment include Cerious Software's Thumbs Plus, TriVista Technology's Simple Landscape and Photo GoRound, and our Zoomable Image Browser based on Pad++.} } @INPROCEEDINGS{lim99a ,AUTHOR = "Joo-Hwee Lim" ,TITLE = "Learnable Visual Keywords for Image Classification" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,abstract = {Automatic categorization of multimedia documents is an important function for a digital library system. While text categorization has received much attentions by IR researchers, classification of visual data is at its infancy stage. In this paper, we propose a notion of visual keywords for similarity matching between visual contents. Visual keywords can be constructed automatically from samples of visual data through supervised/unsupervised learning. Given a visual content, the occurrences of visual keywords are detected, summarized spatially, and coded via singular value decomposition to arrive at a concise coded description. The methods to create, detect, summarize, select, and code visual keywords will be detailed. Last but not least, we describe an evaluation experiment that classifies professional nature scenery photographs to demonstrate the effectiveness and efficiency of visual keywords for automatic categorization of images in digital libraries.} } @INPROCEEDINGS{wech99a ,AUTHOR = "Martin Wechsier and Peter Schauble" ,TITLE = "A New Ranking Principle for Multimedia Information Retrieval" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "relevance ranking, optimal search performance" ,abstract = {A theoretic framework for multimedia information retrieval is introduced which guarantees optimal retrieval effectiveness. In particular, a Ranking Principle for Distributed Multimedia-Documents (RPDM) is described together with an algorithm that satisfies this principle. Finally, the RPDM is shown to be a generalization of the Probability Ranking principle (PRP) which guarantees optimal retrieval effectiveness in the caSe of text document retrieval. The PRP justifies theoretically the relevance ranking adopted by modern search engines. In contrast to the classical PRP, the new RPDM takes into account transmission and inspection time, and most importantly, aspectual recall rather than simple recall.} } @INPROCEEDINGS{melu99a ,AUTHOR = "Massimo Melucci and Nicola Orio" ,TITLE = "Musical Information Retrieval using Melodic Surface" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "computer music, automatic indexing" ,abstract = {The automatic best-match and content-based retrieval of musical documents against musical queries is addressed in this paper. By "musical documents" we mean scores or performances, while musical queries are supposed to be inserted by final users using a musical interface (GUI or MIDI keyboard). Musical documents lack of separators necessary to detect "lexical units" like text words. Moreover there are many variants of a musical phrase between different works. The paper presents a technique to automatically detect musical phrases to be used as content descriptors, and conflate musical phrase variants by extracting a common stem. An experimental study reports on the results of indexing and retrieval tests using the vector-space model. The technique can complement catalogue-based access whenever the user is unable to use fixed values, or he would find performances or scores being "similar" in content to known ones.} } @INPROCEEDINGS{bain99a ,AUTHOR = "David Bainbridge and Craig G. Nevill-Manning and Ian H. Witten and Lloyd A. Smith and Rodger J. McNab" ,TITLE = "Towards a Digital Library of Popular Music" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "music libraries, music representation, melody matching, optical music recognition, MIDI" ,abstract = {Digital libraries of music have the potential to capture popular imagination in ways that more scholarly libraries cannot. we are working towards a comprehensive digital library of musical material, including popular music. We have developed new ways of collecting musical material, accessing it through searching and browsing, and presenting the results to the user. We work with different representations of music: facsimile images of scores, the internal representation of a music editing program, page images typeset by a music editor, MIDI files, audio files representing sung user input, and textual metadata such as title, composer and arranger, and lyrics. This paper describes a comprehensive suite of tools that we have built for this project. These tools gather musical material, convert between many of these representations, allow searching based on combined musical and textual criteria, and help present the results of searching and browsing. Although we do not yet have a single fully-blown digital music library, we have built several exploratory prototype collections of music, some of them very large (100,000 tunes), and critical components of the system have been evaluated.} } @INPROCEEDINGS{dush99a ,AUTHOR = "Naomi Dushay and James C. French and Carl Lagoze" ,TITLE = "Using Query Mediators for Distributed Searching in Federated Digital Libraries" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "distributed searching, query routing, search engine performance" ,abstract = {Resource discovery in a distributed digital library poses many challenges, one of which is how to choose search engines for query distribution. In this paper, we describe a federated, distributed digital library architecture and introduce the notion of a query mediator as a digital library service responsible for selecting among available search engines, routing queries to those search engines, and aggregating results. We examine operational data from the NCSTRL digital library, focusing on two characteristics of distributed resource discovery: availability (will a search engine respond within a time limit) and response time (how quickly will a search engine respond, given that it does respond) and distinguishing between the query mediator view of these characteristics and the indexer view. We also examine the accuracy of predictions we made of QM-view availability and response times of search engines.} } @INPROCEEDINGS{lark99a ,AUTHOR = "Leah S. Larkey" ,TITLE = "A Patent Search and Classification System" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "text categorization" ,abstract = {We present a system for searching and classifying U.S. patent documents, based on Inquery. Patents are distributed through hundreds of collections, divided up by general area. The system selects the best collections for the query. Users can search for pants or classify patent text. The user interface helps users search in fields without requiring the knowledge of Inquery query operators. The system includes a unique "phrase help" facility, which helps users find and add phrases and terms related to those in their query.} } @INPROCEEDINGS{mcgr99a ,AUTHOR = "Robert E. McGrath and Joe Futrelle and Ray Plante" ,TITLE = "Digital Library Technology for Locating and Accessing Scientific Data" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "astronomy data" ,abstract = {In this paper we describe our efforts to bring scientific data into the digital library. This has required extension of the standard WWW, and also the extension of metadata standards far beyond the Dublin Core. Our system demonstrates this technology for real scientific data from astronomy.} } @INPROCEEDINGS{park99a ,AUTHOR = "Soyeon Park" ,TITLE = "User Preferences When Searching Individual and Integrated Full-text Databases" ,BOOKTITLE = dl99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "human computer interaction, distributed information environment, interface design" ,abstract = {This paper addresses a crucial issue in the digital library environment: how to support effective interaction of users with heterogeneous and distributed information resources. We compared users' preference for systems which implement interaction with multiple databases through a common interface and with multiple databases as if they were one (integrated interaction) in an experiment in the Text REtrieval Conference (TREC) environment. Twenty-eight volunteers were recruited from the graduate students of School of Communication, Information, & Library Studies at Rutgers University. Significantly more subjects preferred the common interface (HERMES) to the integrated interface (HERA). For most of the subjects in this study, the greater control in HERMES outweighed the advantages of HERA such as convenience, efficiency, and ease of use. These results suggest that: (1) the general assumption of the information retrieval (IR) literature that an integrated interaction is best needs to be revisited; (2) it is important to allow for more user control in various ways in the distributed environment; and (3) for digital library purposes, it is important to characterize different databases to support user choice for integration.} } @INPROCEEDINGS{alme99a ,AUTHOR = "Virgilio A.F. Almeida and Wagner Meira Jr. and Vicotr F. Ribeiro and Nivio Ziviani" ,TITLE = "Efficiency Analysis of Brokers in the Electronic Marketplace " ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "electronic commerce, e-brokers" ,abstract = {In this paper we analyze the behavior of e-commerce users based on actual logs from two large non-English e-brokers. We start by presenting a quantitative study of the behavior of e-brokers and discuss the influence of regional and cultural issues on them. We then discuss a model that quantifies the efficiency of the results provided by brokers in the electronic marketplace. This model is a function of factors such as server response time and regional factors. Our findings clearly indicate that e-commerce is strongly tied to local language, national customs and regulations, currency conversion and logistics, and Internet infrastructure. We found that the behavior of customers of online bookstores is strongly affected by brand and regional factors. Music CD shoppers show a different behavior that might stem from the fact that music is universal and not so language dependent.} } @INPROCEEDINGS{anup99a ,AUTHOR = "Vinod Anupam and Alain Mayer and Kobbi Nissim and Benny Pinkas and Michael K. Reiter" ,TITLE = "On the Security of Pay-per-click and Other Web Advertising Schemes" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "electronic commerce, secure systems" ,abstract = {We present a hit inflation attack on pay-per- click Web advertising schemes. Our attack is virtually impossible for the program provider to detect conclusively, regardless of whether the provider is a third- party `ad network` or the target of the click itself. If practiced widely, this attack could accelerate a move away from pay- per-click program, and toward programs in which referrers are paid only if the referred user subsequently makes a purchase (pay-per-sale) or engages in other substantial activity at the target site (pay-per-lead). We also briefly discuss the lack of auditability inherent in these schemes.} } @INPROCEEDINGS{jako99a ,AUTHOR = "Markus Jakobsson and Philip D. MacKenzie and Julien P. Stern" ,TITLE = "Secure and Lightweight Advertising on the Web" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "coupons, market model" ,abstract = {We consider how to obtain a safe and efficient scheme for Web advertising. We introduce to cryptography the market model, a common concept from economics. This corresponds to an assumption of rational behavior of protocol participants. Making this assumption allows us to design schemes that are highly efficient in the common case - which is, when participants behave rationally. We demonstrate such a scheme for Web advertising. employing the concept of e-coupons. We prove that our proposed scheme is safe and meets our stringent security requirements.} } @INPROCEEDINGS{sode99a ,AUTHOR = "Caj Sodergard and Matti Aaltonen and Sari Hagman and Mikko Hiirsalmi and Timo Jarvinen and Eija Kaasinen and Timo Kinnunen and Juha Kolari and Jouko Kunnas and Antti Tammela" ,TITLE = "Integrated Multimedia Publishing: Combining TV and Newspaper Content on Personal Channels" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "personalisation, proxy servers" ,abstract = {Fast networks enable the delivery of TV and newspaper content over an Internet connection. This enables new types of integrated publications that include features from both media. The IMU system, described in this paper, automatically integrates newspaper and TV content into a continuously updated World Wide Web-multimedia publication. An active proxy server pursues the integration and delivers the publication through an ATM fibre link to fast networks, such as the bi-directional cable TV network and the ADSL telephone network, providing near-TV quality. The users read the IMU publication from the Internet on their PCs with normal World Wide Web-browsers. You can also watch the publication on your Internet TV set. The proxy server captures metadata from the Web sites and from the editorial systems of the IMU content providers. In addition, the system keeps track of the choices of the user and proposes what news the user and his/her social group would most probably be interested in. The user interface is based on personalisable channels, which gather news material according to the priorities defined by the editors and the users. For ease of use the proxy server automatically Paginates the articles into a sequence of browsable pages. News articles and TV news are linked to each other through automatic association. In a field trial lasting eight months, 62 people used the service through the bi-directional cable TV network in their homes. The average IMU session was brief, focusing on a few and fresh articles, and took place in the evening at prime time or in the morning. Both TV and newspaper content interested the users. Personalisation was not too attractive - only some of the users created their own channels. In the user interviews, the integration of content was VIewed as the key feature.} } @INPROCEEDINGS{jones99a ,AUTHOR = "Matt Jones and Gary Marsden and Norliza Mohd-Nasir and Kevin Boone and George Buchanan" ,TITLE = "Improving Web Interaction on Small Displays" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "handheld computers, mobile computers, small screen display" ,abstract = {Soon many people will retrieve information from the Web using handheld, palmsized or even smaller computers. Although these computers have dramatically increased in sophistication, their display size is - and will remain - much smaller than their conventional, desktop counterparts. Currently, browsers for these devices present Web pages without taking account of the very different display capabilities. As part of a collaborative project with Reuters, we carried out a study into the usability impact of small displays for retrieval tasks. Users of the small screen were 50% less effective in completing tasks than the large screen subjects. Small screen users used a very substantial number of scroll activities in attempting to complete the tasks. Our study also provided us with interesting insights into the shifts in approach users seem to make when using a small screen device for retrieval. These results suggest that the metaphors useful in a full screen desktop environment are not the most appropriate for the new devices. Design guidelines are discussed, here, Proposing directed access methods for effective small screen interaction. In our ongoing work, we are developing such 'meta-interfaces' which will sit between the small screen user and the `conventional' Web page.} } @INPROCEEDINGS{barg99a ,AUTHOR = "David Bargeron and Anoop Gupta and Jonathan Grudin and Elizabeth Sanocki" ,TITLE = "Annotations for streaming video on the Web: System Design and Usage Studies" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "video annotation, multimedia annotation, asynchronous collaboration" ,abstract = {Streaming video on the World Wide Web is being widely deployed, and workplace training and distance education are key applications. The ability to annotate video on the Web can provide significant added value in these and other areas. Written and spoken annotations can provide `in context' personal notes and can enable asynchronous collaboration among groups of users. With annotations, users are no longer limited to viewing content passively on the Web, but are free to add and share commentary and links, thus transforming the Web into an interactive medium. We discuss design considerations in constructing a collaborative video annotation system, and we introduce our prototype, called MRAS. We present preliminary data on the use of Web- based annotations for personal note-taking and for sharing notes in a distance education scenario, Users showed a strong preference for MRAS over pen-and-paper for taking notes, despite taking longer to do so. They also indicated that they would make more abstract and questions with MRAS than in a `live' situation, and that sharing added substantial value.} } @INPROCEEDINGS{deut99a ,AUTHOR = "Alin Deutsch and Mary Fernandez and Daniela Florescu and Alon Levy and Dan Suciu" ,TITLE = "A Query Language for XML" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "electronic-data interchange (EDI)" ,abstract = {An important application of XML is the interchange of electronic data (EDI) between multiple data sources on the Web. As XML data proliferates on the Web, applications will need to integrate and aggregate data from multiple source and clean and transform data to facilitate exchange. Data extraction, conversion, transformation. and integration are all well-understood database problems, and their solutions rely on a query language. We present a query language for XML, called XML-QL, which we argue is suitable for performing the above tasks. XML-QL is a declarative. `relational complete' query language and is simple enough that it can be optimized. XML-QL can extract data from existing XML documents and construct new XML documents.} } @INPROCEEDINGS{ceri99a ,AUTHOR = "Stefano Ceri and Sara Comai and Ernesto Damiani and Piero Fraternali and Stefano Paraboschi and Letizia Tanca" ,TITLE = "XML-GL: A Graphical Language for Wuerying and Restructuring XML Documents" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "query languages, graphical queries" ,abstract = {The growing acceptance of XML as a standard for semi-structured documents on the Web opens up challenging opportunities for Web query languages. In this paper we introduce XML-GL, a graphical query language for XML documents. The use of a visual formalism for representing both the content of XML documents (and of their DTDs) and the syntax and semantics of queries enables an intuitive expression of queries, even when they are rather complex. XML-GL is inspired by G-log, a general purpose, logic-based language for querying structured and semi-structured data. The paper presents the basic capabilities of XML-GL through a sequence of examples of increasing complexity.} } @INPROCEEDINGS{kris99a ,AUTHOR = "Anders Kristensen" ,TITLE = "Formsheets and the XML Forms Language" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "XForm, XSL" ,abstract = {This paper presents XForm - a proposal for a general and powerful mechanism for handling forms in XML. XForm defines form - related constructs independent of any particular XML language and set of form controls. It defines the notion of formsheets as a mechanism for computing form values on the client, form values being arbitrary, typed XML documents. This enables a symmetrical exchange of data between clients and servers which is useful for example for database and workflow applications. Formsheets can be written in a variety of languages - we argue that the document transformation capabilities of XSL stylesheets make them an elegant choice.} } @INPROCEEDINGS{karg99a ,AUTHOR = "David Karger and Alex Sherman and Andy Berkheimer and Bill Bogstad and Rizwan Dhanidina and Ken Iwamoto and Brian Kim and Luke Matkins and Yoav Yerushalmi" ,TITLE = "Web Caching with Consistent Hashing" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "load balancing" ,abstract = {A key performance measure for the World Wide Web is the speed with which content is served to users. As traffic on the Web increases, users are faced with increasing delays and failures in data delivery. Web caching is one of the key strategies that has been explored to improve performance. An important issue in many caching systems is how to decide what is cached where at any given time. Solutions have included multicast queries and directory schemes. In this paper, we offer a new Web caching strategy based on consistent hashing. Consistent hashing provides an alternative to multicast and directory schemes, and has several other advantages in load balancing and fault tolerance. Its performance was analyzed theoretically in previous work: in this paper we describe the implementation of a consistent-hashing-based system and experiments that support our thesis that it can provide performance improvements.} } @INPROCEEDINGS{bake99a ,AUTHOR = "Scott M. Baker and Bongki Moon" ,TITLE = "Distributed Cooperative Web Servers" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "scalable web servers, document migration, load balancing" ,abstract = {Traditional techniques for a distributed web server design rely on manipulation of central resources, such as routers or DNS services, to distribute requests designated for a single IP address to multiple web servers. The goal of the distributed cooperative Web server (DCWS) system development is to explore application-level techniques for distributing web content. We achieve this by dynamically manipulating the hyperlinks stored within the web documents themselves. The DCWS system effectively eliminates the bottleneck of centralized resources, while balancing the load among distributed web servers. DCWS servers may be located in different networks, or even different continents and still balance load effectively. DCWS system design is fully compatible with existing HTTP protocol semantics and existing web client software products.} } @INPROCEEDINGS{will99a ,AUTHOR = "Craig E. Wills and Mikhail Mikhailov" ,TITLE = "Towards a Better Understanding of Web Resources and Server Responses for Improved Caching" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,abstract = {This work focuses on characterizing information about Web resources and server responses that is relevant to Web caching. The approach is to study a set of URLs at a variety of sites and gather statistics about the rate and nature of changes compared with the resource type. In addition, we gather response header information reported by the servers with each retrieved resource. Results from the work indicate that there is potential to reuse more cached resources than is currently being realized due to inaccurate and nonexistent cache directives. In terms of implications for caching, the relationships between resources used to compose a page must be considered. Embedded images are often reused, even in pages that change frequently. This result both points to the need to cache such images and to discard them when they are no longer included as part of any page. Finally, while the results show that HTML resources frequently change, these changes can be in a predictable and localized manner. Separating out the dynamic portions of a page into their own resources allows relatively static portions to be cached, while retrieval of the dynamic resources can trigger retrieval of new resources along with any invalidation of already cached resources.} } @INPROCEEDINGS{henz99a ,AUTHOR = "Monika R. Henzinger and Allan Heydon and Michael Mitzenmacher and Marc Najork" ,TITLE = "Measuring Index Quality Using Random Wals on the Web" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "PageRank" ,abstract = {Recent research has studied how to measure the size of a search engine, in terms of the number of pages indexed. In this paper, we consider a different measure for search engines, namely the quality of the pages in a search engine index. We provide a simple, effective algorithm for approximating the quality of an index by performing a random walk on the Web, and we use this methodology to compare the index quality of several major search engines.} } @INPROCEEDINGS{jenk99a ,AUTHOR = "Charlotte Jenkins and Mike Jackson and Peter Burden and Jon Wallis" ,TITLE = "Automatic RDF Metadata Generation for Resource Discovery" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "classification" ,abstract = {Automatic metadata generation may provide a solution to the problem of inconsistent, unreliable metadata describing resources on the Web. The Resource Description Framework (RDF) provides a domain-neutral foundation on which extensible element sets can be defined and expressed in a standard notation. This paper describes how an automatic classifier, that classifies HTML documents according to Dewey Decimal Classification, can be used to extract context sensitive metadata which is then represented using RDF. The process of automatic classification is described and an appropriate metadata element set is identified comprising those elements that can be extracted during classification. An RDF data model and an RDF schema are defined representing the element set and the classifier is configured to output the elements in RDF syntax according to the defined schema.} } @INPROCEEDINGS{hawk99a ,AUTHOR = "David Hawking and Nick Craswell and Paul Thistlewaite and Donna Harman" ,TITLE = "Results and Challenges in Web Search Evaluation" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "TREC, test collection" ,abstract = {A frozen 18.5 million page snapshot of part of the Web has been created to enable and encourage meaningful and reproducible evaluation of Web search systems and techniques. This collection is being used in an evaluation framework within the Text Retrieval Conference (TREC) and will hopefully provide convincing answers to questions such as, "Can link information result in better rankings?`, "Do longer queries result in better answers?`, and, "Do TREC systems work well on Web data?" The snapshot and associated evaluation methods are described and an invitation is extended to participate. Preliminary results are presented for an effective comparison of six TREC systems working on the snapshot collection against five well-known Web search systems working over the current Web. These suggest that the standard of document rankings produced by public Web search engines is by no means state-of-the-art.} } @INPROCEEDINGS{gron99a ,AUTHOR = "Kaj Gronbaek and Lennert Sloth and Peter Orbaek" ,TITLE = "Webvise: Browser and Proxy Support for Open Hypermedia Structuring Mechanisms on the World Wide Web" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "information structuring, navigation, collaboration, DOM" ,abstract = {This paper discusses how to augment the World Wide Web with an open hypermedia service (Webvise) that provides structures such as contexts, links, annotations, and guided tours stored in hypermedia databases external to the Web pages. This includes the ability for users collaboratively to create links front parts of HTML Web pages they do not own and support for creating links to parts of Web pages without writing HTML target tags. The method for locating parts of Web pages can locate parts of pages across frame hierarchies and it also supports certain repairs of links that break due to modified Web pages. Support for providing links to/from parts of non-HTML data, such as sound and movie, will be possible via interfaces to plug-ins and Java-based media players. The hypermedia structures are stored in a hypermedia database, developed from the Devise Hypermedia framework, and the service is available on the Web via an ordinary URL. The best user interface for creating and manipulating the structures is currently provided for the Microsoft Internet Explorer 4.x browser through COM integration that utilizes the Explorer's DOM representation of Web-pages. But the structures can also be manipulated and used via special Java applets and a pure proxy server solution is provided for users who only need to browse the structures. A user can create and use the external structures as `transparency' layers on top of arbitrary Web pages, the user can switch between viewing pageswith one or more layers (contexts) of structures or without any external structures imposed on them.} } @INPROCEEDINGS{chid99a ,AUTHOR = "Boris Chidlovskii and Claudia Roncancio and Marie-Luise Schneider" ,TITLE = "Semantic Cache Mechanism for Heterogeneous Web Querying" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "semantic cache, source heterogeneity, meta-searcher" ,abstract = {In Web-based searching systems that access distributed information providers, efficient query processing requires an advanced caching mechanism to reduce the query response time. The keyword-based querying is often the only way to retrieve data from Web providers, and therefore standard page-based and tuple- based caching mechanisms turn out to be improper for such a task. In this work, we develop a mechanism for efficient caching of Web queries and the answers received from heterogeneous Web providers. We also report results of experiments and show how the caching mechanism is implemented in the Knowledge Broker system.} } @INPROCEEDINGS{zami99a ,AUTHOR = "Oren Zamir and Oren Etzioni" ,TITLE = "Grouper: A Dynamic Clustering Interface to Web Search Results" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "document clustering, visualization" ,abstract = {Users of Web search engines are often forced to sift through the long ordered list of document `snippets' returned by the engines. The IR community has explored document clustering as an alternative method of organizing retrieval results, but clustering has yet to be deployed on most major search engines. The NorthernLight search engine organizes its output into `custom folders' based on pre-computed document labels, but does not reveal how the folders are generated or how well they correspond to users interests. In this paper, we introduce Grouper, an interface to the results of the HuskySearch meta-search engine, which dynamically groups the search results into clusters labeled by phrases extracted from the snippets. In addition, we report on the first empirical comparison of user Web search behavior on a standard ranked-list presentation versus a clustered presentation. By analyzing HuskySearch logs, we are able to demonstrate substantial differences in the number of documents followed, and in the amount of time and effort expended by users accessing search results through these two interfaces.} } @INPROCEEDINGS{Liwe99a ,AUTHOR = "Wen-Syan Li and Quoc Vu and Divakant Agrawal and Yoshinori Hara and Hajime Takano" ,TITLE = "PowerBookmarks: A System for Personalizable Web Information Organization, Sharing, and Management" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "personalization, classification" ,abstract = {We extend the notion of bookmark management by introducing the functionalities of hypermedia databases. Power- Bookmarks is a Web information organization, sharing, and management tool, which parses metadata from bookmarked URLs and uses it to index and classify the URLs. PowerBookmarks supports advanced query, classification, and navigation functionalities on collections of bookmarks. PowerBookmarks monitors and utilizes users' access patterns to provide many useful personalized services, such as automated URL bookmarking, document refreshing, and bookmark expiration. It also allows users to specify their preference in bookmark management, such as ranking schemes and classification tree structures. Subscription services for new or updated documents of users' interests are also supported.} } @INPROCEEDINGS{brab99a ,AUTHOR = "Claus Brabrand and Anders Moller and Anders Sandholm and Michael I. Schwartzbach" ,TITLE = "A Runtime System for Interactive Web Services" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "CGI, runtime system" ,abstract = {Interactive Web services are increasingly replacing traditional static Web pages. Producing Web services seems to require a tremendous amount of laborious low-level coding due to the primitive nature of CGI programming. We present ideas for an improved runtime system for interactive Web services built on top of CGI running on virtually every combination of browser and HTTP/CGI server. The runtime system has been implemented and used extensively in . a tool for producing interactive Web services.} } @INPROCEEDINGS{mart99a ,AUTHOR = "Philippe Martin and Peter Eklund" ,TITLE = "Embedding Knowledge in Web Documents" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "knowledge modeling, precision-oriented information retrieval, knowledge-based indexation and annotation, ontology" ,abstract = {The paper argues for the use of general and intuitive knowledge representation languages (and simpler notational variants, e.g. subsets of natural languages) for indexing the content of Web documents and representing knowledge within them. We believe that these languages have advantages over metadata languages based on the Extensible Mark-up Language (XML). Indeed, the retrieval of precise information is better supported by languages designed to represent semantic content and support logical inference, and the readability of such a language eases its exploitation, presentation and direct insertion within a document (thus also avoiding information duplication). We advocate the use of Conceptual Graphs and simpler notational variants that enhance knowledge readability. To further ease the representation process, we propose techniques allowing users to leave some knowledge terms undeclared. We also show how lexical, structural and knowledge-based techniques may be combined to retrieve or generate knowledge or Web documents. To support and guide the knowledge modeling approach, we present a top-level ontology of 400 concept and relation types. We have implemented these features in a Web-accessible tool named WebKB, and show examples to illustrate them. } } @INPROCEEDINGS{dean99a ,AUTHOR = "Jeffrey Dean and Monika R. Henzinger" ,TITLE = "Finding Related Pages in the World Wide Web" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "search engines, related pages, searching paradigms" ,abstract = {When using traditional search engines, users have to formulate queries to describe their information need. This paper discusses a different approach to Web searching where the input to the search process is not a set of query terms, but instead is the URL of a page, and the output is a set of related Web pages. A related Web page is one that addresses the same topic as the original page. For example, www.washingtonpost.con is a page related to www.nytimes.con, since both are online newspapers. We describe two algorithms to identify related Web pages. These algorithms use only the connectivity information in the Web (i.e., the links between pages) and not the content of pages or usage information. We have implemented both algorithms and measured their runtime performance. To evaluate the effectiveness of our algorithms, we performed a user study comparing our algorithms with Netscape's `What's Related' service (http://home.netscape.con/escapes/related/). Our study showed that the precision at 10 for our two algorithms are 73% better and 51% better than that of Netscape, despite the fact that Netscape uses both content and usage pattern information in addition to connectivity information.} } @INPROCEEDINGS{kuma99a ,AUTHOR = "Ravi Kumar and Prabhakar Raghavan and Sridhar Rajagopalan and Andrew Tomkins" ,TITLE = "Trawling the Web for emerging cyber-communities" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "web mining, link analysis" ,abstract = {The Web harbors a large number of communities - groups of content-creators sharing a common interest - each of which manifests itself as a set of interlinked Web pages. Newgroups and commercial Web directories together contain of the order of 20,000 such communities; our particular interest here is on emerging communities - those that have little or no representation in such fora. The subject of this paper is the systematic enumeration of over 100,O0O such emerging communities from a Web crawl: we call our process trawling. We motivate a graph-theoretic approach to locating such communities, and describe the algorithms, and the algorithmic engineering necessary to find structures that subscribe to this notion, the challenges in handling such a huge data set, and the results of our experiment.} } @INPROCEEDINGS{guan99a ,AUTHOR = "Tao Guan and Kam-Fai Wong" ,TITLE = "KPS: a Web Information Mining Algorithm" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "information extraction, web query, web databases" ,abstract = {The Web mostly contains semi-structured information. It is, however, not easy to search and extract structural data hidden in a Web page. Current practices address this problem by (1) syntax analysis (i.e. HTML tags); or (2) wrappers or user-defined declarative languages. The former is only suitable for highly structured Web sites and the latter is time-consuming and offers low scalability. Wrappers could handle tens, but certainly not thousands, of information sources. In this paper, we present a novel information mining algorithm, namely KPS, over semi-structured information on the Web. KPS employs keywords, patterns and/or samples to mine the desired information. Experimental results show that KPS is more efficient than existing Web extracting methods.} } @INPROCEEDINGS{wan99a ,AUTHOR = "Ernest Wan and Philip Robertson and John Brook and Stephen Bruce and Kristine Armitage" ,TITLE = "Retaining Hyperlinks in Printed Hypermedia Document" ,BOOKTITLE = www99 ,entered-by = "Rebecca Wesley" ,keywords = "cut-out-tab" ,abstract = {In this paper, we describe a method that allows a hypermedia document to retain its hyperlinks in the printed copy. The method associates the hyperlinks with cut-out tabs on the edges of the printed pages. A method for modelling the cut-out tabs and optimizing their assignment to the hyperlinks is discussed. We also describe a prototype authoring system that implements the method.} } @INPROCEEDINGS{kope99a ,AUTHOR = "Theodorich Kopetzky and Max Muhlhauser" ,TITLE = "Visual Preview for Link Traversal on the World Wide Web" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "hypertext navigation, user interface, link preview" ,abstract = {This paper demonstrates a technique for augmenting current World Wide Web browser implementations with features found in classical, hypertext applications but unknown to the World Wide Web community until now. An example implementation is shown using Netscape Navigator 4.x using JavaScript, dynamic HTML and Java. The implementation follows an architecture based on a proxy server which acts as a gateway between the Internet and the browsing client. Based on the detailed example, support for further features is discussed.} } @INPROCEEDINGS{stan99a ,AUTHOR = "Dominic Stanyer and Rob Procter" ,TITLE = "Improving Web Usability with the Link Lens" ,BOOKTITLE = www99 ,entered-by = "Rebecca Wesley" ,keywords = "user interface, quality of service, download delays" ,abstract = {A number of factors may influence Web users' choice of which links to follow. These include assumptions about document quality and anticipated retrieval times. The present generation of World Wide Web browsers, however, provide only minimal support to assist users in making informed decisions. Web browser `link user interfaces' typically only display a document's Universal Resource Locator CURL), whilst a simple binary colour change in the URL's anchor is used to indicate its activation history. The question then is, how do users deal with the problem of having to make such decisions when the information at hand is insufficient? We have been conducting an investigation of how users make link selections.The results show users often are forced to fall back on heuristics and improvising strategies drawn from past experience. Based upon these results, we present a prototype of the `link lens', an enhanced link user interface designed to make such decisions easier and more productive for all users and help less experienced ones gain a better understanding of Web behaviour.} } @INPROCEEDINGS{rabi99a ,AUTHOR = "Michael Rabinovich and Amit Aggarwal" ,TITLE = "RaDaR: a Scalable Architecture for a Global Web Hosting Service" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "dynamic replication, migration" ,abstract = {As commercial interest in the Internet grows, more and more companies are offering the service of hosting and providing access to information that belongs to third-party information providers. In the future, successful hosting services may host millions of objects on thousands of servers deployed around the globe. To provide reasonable access performance to popular resources, these resources will have to be mirrored on multiple servers. In this paper, we identify some challenges due to the scale that a platform for such global services would face, and propose an architecture capable of handling this scale. The proposed architecture has no bottleneck points. A trace-driven simulation using an access trace from AT&T's hosting service shows very promising results for our approach.} } @INPROCEEDINGS{abde99a ,AUTHOR = "Tarek F. Abdelzaher and Nina Bhatti" ,TITLE = "Web Content Adaptation to Improve Server Overload Behavior" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "web server performance, adaptive content, overload protection" ,abstract = {This paper presents a study of Web content adaptation to improve server overload performance, as well as an implementation of a' Web content adaptation software prototype. When the request rate on a Web server increases beyond server capacity, the server becomes overloaded and unresponsive. The TCP listen queue of the server's socket overflows exhibiting a drop-tail behavior. As a result, clients experience service outages. Since clients typically issue multiple requests over the duration of a session with the server, and since requests are dropped indiscriminately, all clients connecting to the server at overload are likely to experience connection failures, even though there may be enough capacity on the server to deliver all responses properly for a subset of clients. In this paper, we propose to resolve the overload problem by adapting delivered content to load conditions to alleviate overload. The premise is that successful delivery of a less resource intensive content under overload is more desirable to clients than connection rejection or failures.} } @INPROCEEDINGS{bhar99a ,AUTHOR = "Krishna Bharat and Andrei Broder" ,TITLE = "Mirror, Mirror on the Web: A Study of Host Pairs with Replicated Content" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "mirroring, content duplication, smart proxies, smart crawlers, web statistics" ,abstract = {TWO previous studies. one done at Stanford in 1997 based on data collected by the Google search engine, and one done at Digital in 1996 based on AltaVista data, revealed that almost a third of the Web consists of duplicate pages. Both studies identified mirroring, that is, the systematic replication of content over a pair of hosts, as the principal cause of duplication, but did not further investigate this phenomenon. The main aim of this paper is to present a clearer picture of mirroring on the Web. As input we used a set of 179 million URLs found during a Web crawl done in the summer of 1998. We looked at all hosts with more than 100 URLs in our input (about 238,000), and discovered that about 10% were mirrored to varying degrees. The paper presents data about the prevalence of mirroring based on a mirroring classification scheme that we define. There are numerous reasons for mirroring: technical (e.g., to improve access time), commercial (e.g., different intermediaries offering the same products), cultural (e.g., same content in two languages), social (e.g.. sharing of research data). and so forth. Although we have not done a exhaustive study of the causes of replication, we discuss and provide examples for several representative cases. Our technique for detecting mirrored hosts from large sets of collected URLs depends mostly on the syntactic analysis of URL strings, and requires retrieval and content analysis only for a small number of pages. We are able to detect both partial and total mirroring, and handle cases where the content is not byte-wise identical. Furthermore, our technique is computationally very efficient and does not assume that the initial set of URLs gathered from each host is comprehensive. Hence, this approach has practical uses beyond our study, and can be applied in other settings. For instance, for Web crawlers and caching proxies, detecting mirrors can be valuable to avoid redundant fetching. and knowledge of mirroring can be used to compensate for broken links.} } @INPROCEEDINGS{chan99b ,AUTHOR = "Alvin T.S. Chan" ,TITLE = "Web-enabled Smart Card for Ubiquitous Access of Patient's Medical Record" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "smart card" ,abstract = {The combined benefits of smart card to support mobility in a pocket coupled with the ubiquitous access of Web technology, present a new paradigm for medical information access systems. The paper describes the framework of Java Card Web Servlet (JCWS) that is being developed to provide seamless access interface between a Web browser and a Java-enabled smart card. Importantly, the smart card is viewed as a mobile repository of Web objects comprised of HTML pages, medical data objects, and record browsing and updating applet. As the patient moves between hospitals, clinics and countries, the mobility of the smart-card database dynamically binds to the JCWS framework to facilitate a truly ubiquitous access and updating of medical information via a standard Web-browser interface.} } @INPROCEEDINGS{kaha99a ,AUTHOR = "Jose Kahan" ,TITLE = "WDAI: A Simple World Wide Web Distributed Authorization Infrastructure" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "distributed hypermedia, security, access control" ,abstract = {The World Wide Web (W3) has the potential to link different kinds of documents into hypertext collections and to distribute such collections among many document servers. Distributed collections can bring forth new W3 applications in extranets and expand the concept of content reuse. However, they also bring new authorization problems. such as the need for coordinated user administration, user authentication, and revocation of rights. This paper proposes WDAI. a simple and general infrastructure for distributed authorization on the World Wide Web. Under WDAI, browsers and servers exchange authorization information using X.S09v3-based authorization certificates. WDAI is designed to be open to a wide variety of security policies and, being compatible with existing W3 technology, can be implemented without modifying existing browsers.} } @INPROCEEDINGS{blai99a ,AUTHOR = "Barclay Blair and John Boyer" ,TITLE = "XFDL: Creating Electronic Commerce Transaction Records Using XML" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "electronic records, records management" ,abstract = {In the race to transform the World Wide Web from a medium for information presentation to a medium for information exchange, the development of practices for ensuring the security, auditability, and non- repudiation of transactions that are well established in the paper-based world has not kept pace in the digital world. Existing Internet technology provides no easy way to create a valid `digital receipt' that meets the requirements of both complex distributed networks and the business community. In addition, an improved articulation of digital signatures is needed. Extensible Forms Description Language (XFDL), developed by UWI.Com and Tim Bray, is an application of XML that allows organizations to move their paper-based forms systems to the Internet while maintaining the necessary attributes of paper-based transaction records. XFDL was designed for implementation in business-to-business electronic commerce and intra-organizational information transactions.} } @INPROCEEDINGS{chak99a ,AUTHOR = "Soumen Chakrabarti and Martin van den Berg and Byron Dom" ,TITLE = "Focused Crawling: A New Approach to Topic-specific Web Resource Discovery" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "classification, categorization, topic distillation" ,abstract = {The rapid growth of the World-Wide Web poses unprecedented scaling challenges for general-purpose crawlers and search engines. In this paper we describe a new hypertext resource discovery system called a Focused Crawler. The goal of a focused crawler is to selectively seek out pages that are relevant to a pre-defined set of topics. The topics are specified not using keywords, but using exemplary documents. Rather than collecting and indexing all accessible Web documents to be able to answer all possible ad-hoc queries, a focused crawler analyzes its crawl boundary to find the links that are likely to be most relevant for the crawl, and avoids irrelevant regions of the Web. This leads to significant savings in hardware and network resources, and helps keep the crawl more up-to-date. To achieve such goal-directed crawling, we designed two hypertext mining programs that guide our crawler: a classifier that evaluates the relevance of a hypertext document with respect to the focus topics, and a distiller that identifies hypertext nodes that are great access points to many relevant pages within a few links. We report on extensive focused-crawling experiments using several topics at different levels of specificity. Focused crawling acquires relevant pages steadily while standard crawling quickly loses its way, even though they are started from the same root set. Focused crawling is robust against large perturbations in the starting set of URLs. It discovers largely overlapping sets of resources in spite of these perturbations. It is also capable of exploring out and discovering valuable resources that are dozens of links away from the start set, while carefully pruning the millions of pages that may lie within this same radius. Our anecdotes suggest that focused crawling is very effective for building high-quality collections of Web documents on specific topics, using modest desktop hardware.} } @INPROCEEDINGS{cohe99a ,AUTHOR = "William W. Cohen and Wei Fan" ,TITLE = "Learning Page-independent Heuristics for Extracting Data from Web Pages" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "information integration, machine learning, extraction" ,abstract = {One bottleneck in implementing a system that intelligently queries the Web is developing `wrappers' - programs that extract data from Web pages. Here we describe a method for learning general, page-independent heuristics for extracting data from HTML documents. The input to our learning system is a set of working wrapper programs, paired with HTML pages they correctly wrap. The output is a general procedure for extracting data that works for many formats and many pages. In experiments with a collection of 84 constrained but realistic extraction problems, we demonstrate that 30% of the problems can be handled perfectly by learned extraction heuristics, and around 50% can be handled acceptably. We also demonstrate that learned page-independent extraction heuristics can substantially improve the performance of methods for learning page-specific wrappers.} } @INPROCEEDINGS{bens99a ,AUTHOR = "Israel Ben-Shaul and Michael Herscovici and Michal Jacovi and Yoelle S. Maarek and Dan Pelleg and Menachem Shtalhaim and Vladimir Soroka and Sigalit Ur" ,TITLE = "Adding Support for Dynamic and Focused Search with Fetuccino" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "search enhancements, search filtering, search results visualization, site mapping" ,abstract = {This paper proposes two enhancements to existing search services over the Web. One enhancement is the addition of limited dynamic search around results provided by regular Web search services, in order to correct part of the discrepancy between the actual Web and its static image as stored in search repositories. The second enhancement is an experimental two-phase paradigm that allows the user to distinguish between a domain query and a focused query within the dynamically identified domain. We present Fetuccino, an extension of the Mapuccino system that implements these two enhancements. Fetuccino provides an enhanced user-interface for visualization of search results, including advanced graph layout, display of structural information and support for standards (such as XML). While Fetuccino has been implemented on top of existing search services, its features could easily be integrated into any search engine for better performance. A light version of Fetuccino is available on the Internet at http://www.ibm.com/java/fetuccino.} } @INPROCEEDINGS{ross99a ,AUTHOR = "Gustavo Rossi and Daniel Schwabe and Fernando Lyardet" ,TITLE = "Improving Web Information Systems with Navigational Patterns" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "web information systems, hypermedia design, navigation design" ,abstract = {In this paper we show how to improve the architecture of Web information systems (WIS) using design patterns. in particular navigational patterns. We first present a framework to reason about the process of designing and implementing these applications. Then we introduce navigational patterns and show some prototypical patterns. We next show how these patterns have been used in some successful WIS. Finally, we explain how patterns are integrated into the development process of WIS.} } @INPROCEEDINGS{chak99b ,AUTHOR = "Soumen Chakrabarti and David A. Gibson and Kevin S. McCurley" ,TITLE = "Surfing the Web Backwards" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "backlinks, navigation" ,abstract = {From a user's perspective, hypertext links on the Web form a directed graph between distinct information sources. We investigate the effects of discovering `backlinks' from Web resources, namely links pointing to the resource. We describe fools for backlink navigation on both the client and server side, using an applet for the client and a module for the Apache Web server, We also discuss possible extensions to the HTTP protocol to facilitate the collection and navigation of backlink information in the World Wide Web.} } @INPROCEEDINGS{abra99a ,AUTHOR = "Marc Abrams and Constantinos Phanouriou and Alan L. Batongbacal and Stephen M. Williams and Jonathan E. Shuster" ,TITLE = "UIML: An Appliance-independent XML User Interface Language" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "handheld devices, mobile devices" ,abstract = {Today's Internet appliances feature user interface technologies almost unknown a few years ago: touch screens, styli, handwriting and voice recognition, speech synthesis, tiny screens, and more. This richness creates problems. First. different appliances use different languages: WML for cell phones; SpeechML, JSML, and VoxML for voice enabled devices such as phones; HTML and XUL for desktop computers, and so on. Thus, developers must maintain multiple source code families to deploy interfaces to one information system on multiple appliances. Second, user interfaces differ dramatically in complexity (e.g, PC versus cell phone interfaces). Thus, developers must also manage interface content. Third, developers risk writing appliance-specific interfaces for an appliance that might not be on the market tomorrow. A solution is to build interfaces with a single, universal language free of assumptions about appliances and interface technology. This paper introduces such a language, the User Interface Markup Language (UIML), an XML-compliant language. UIML insulates the interface designer from the peculiarities of different appliances through style sheets. A measure of the power of UIML is that it can replace hand-coding of Java AWT or Swing user interfaces.} } @INPROCEEDINGS{cohe99b ,AUTHOR = "Edith Cohen and Haim Kaplan and Jeffrey Oldham" ,TITLE = "Managing TCP Connections Under Persistent HTTP" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "persistent connections, connection management, caching" ,abstract = {Hyper Text Transfer Protocol (HTTP) traffic dominates Internet traffic. The exchange of HTTP messages is implemented using the connection-oriented TCP. HTTP/l.0 establishes a new TCP connection for each HTTP request, resulting in many consecutive short-lived TCP connections. The emerging HTTP/ 1.1 reduces latencies and overhead from closing and re-establishing connections by supporting persistent connections as a default. A TCP connection which is kept open and reused for the next HTTP request reduces overhead and latency. Open connections, however, consume sockets and memory for socket-buffers. This trade-off establishes a need for connection-management policies. We propose policies that exploit embedded information in the HTTP request messages, e.g., senders' identities and requested URLs. and compare them to the fixed-timeout policy used in the current implementation of the Apache Web server. An experimental evaluation of connection management policies at Web servers, conducted using Web server logs. shows that our URL-based policy consistently outperforms other policies. and achieves significant 15-25% reduction in cost with respect to the fixed-timeout policy. Hence, allowing Web servers and clients to more fully reap the benefits of persistent HTTP.} } @INPROCEEDINGS{bake99b ,AUTHOR = "Scott Baker and John H. Hartman" ,TITLE = "The Gecko NFS Web Proxy" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,keywords = "HTTP, hyperlink" ,abstract = {The World-Wide Web provides remote access to pages using its own naming scheme (URLs). transfer protocol (HTTP), and cache algorithms. Not only does using these special-purpose mechanisms have performance implications, but they make it impossible for standard Unix applications to access the Web. Gecko is a system that provides access to the Web via the NFS protocol. URLs are mapped to Unix file names, providing unmodified applications access to Web pages; pages are transferred from the Gecko server to the clients using NFS instead of HTTP. significantly improving performance; and NFS's cache consistency mechanism ensures that all clients have the same version of a page. Applications access pages as they would Unix files. A client-side proxy translates HTTP requests into file accesses, allowing existing Web applications to use Gecko. Experiments performed on our prototype show that Gecko is able to provide this additional functionality at a performance level that exceeds that of HTTP.} } @INPROCEEDINGS{kris99b ,AUTHOR = "Balachander Krishnamurthy and Jeffrey C. Mogul and David M. Kristol" ,TITLE = "Key Differences Between HTTP/1.0 and HTTP/1.1" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Rebecca Wesley" ,abstract = {The HTTP/l.1 protocol is the result of four years of discussion and debate among a broad group of Web researchers and developers. It improves upon its phenomenally successful predecessor, HTTP/1.0, in numerous ways. We discuss the differences between HTTP/1.0 and HITP/l.l, as well as some of the rationale behind these changes.} } @INPROCEEDINGS{hirai00 ,AUTHOR = "Jun Hirai and Sriram Raghavan and Hector Garcia-Molina and Andreas Paepcke" ,TITLE = "WebBase: A repository of web pages" ,BOOKTITLE = www00 ,YEAR = "2000" ,pages = "277--293" ,month = "May" ,note = "Available at http://dbpubs.stanford.edu/pub/2000-51" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-51)" ,entered-by = "Andreas Paepcke" ,keywords = "webbase, value filtering" ,abstract = {In this paper, we study the problem of constructing and maintaining a large shared repository of web pages. We discuss the unique characteristics of such a repository, propose an architecture, and identify its functional modules. We focus on the storage manager module, and illustrate how traditional techniques for storage and indexing can be tailored to meet the requirements of a web repository. To evaluate design alternatives, we also present experimental results from a prototype repository called WebBase, that is currently being developed at Stanford University. Keywords : Repository, WebBase, Architecture, Storage management } } @INPROCEEDINGS{meln99 ,AUTHOR = "Sergey Melnik and Hector Garcia-Molina and Andreas Paepcke" ,TITLE = "A Mediation Infrastructure for Digital Library Services" ,BOOKTITLE = dl00 ,YEAR = "2000" ,note = "Available at http://dbpubs.stanford.edu/pub/1999-25" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1999-25)" ,entered-by = "Andreas Paepcke" ,keywords = "GINF, mediators, mediation architecture, interoperability" ,abstract = {Digital library mediators allow interoperation between diverse information services. In this paper we describe a flexible and dynamic mediator infrastructure that allows mediators to be composed from a set of modules (``blades''). Each module implements a particular mediation function, such as protocol translation, query translation, or result merging. All the information used by the mediator, including the mediator logic itself, is represented by an RDF graph. We illustrate our approach using a mediation scenario involving a Dienst and a Z39.50 server, and we discuss the potential advantages and weaknesses of our framework.} } @INPROCEEDINGS{buyu99 ,AUTHOR = "Orkut Buyukkokten and Hector Garcia Molina and Andreas Paepcke and Terry Winograd" ,TITLE = "Power Browser: Efficient Web Browsing for PDAs" ,BOOKTITLE = chi00 ,YEAR = "2000" ,editor = "~" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1999-32)" ,entered-by = "Andreas Paepcke" ,keywords = "power browser, pda" ,abstract = {We have designed and implemented new Web browsing facilities to support effective navigation on Personal Digital Assistants (PDAs) with limited capabilities: low bandwidth, small display, and slow CPU. The implementation supports wireless browsing from 3Com's Palm Pilot. An HTTP proxy fetches web pages on the client's behalf and dynamically generates summary views to be transmitted to the client. These summaries represent both the link structure and contents of a set of web pages, using information about link importance. We discuss the architecture, user interface facilities, and the results of comparative performance evaluations. We measured a 45% gain in browsing speed, and a 42% reduction in required pen movements.} } @INPROCEEDINGS{buyu99a ,AUTHOR = "Orkut Buyukkokten and Hector Garcia-Molina and Andreas Paepcke" ,TITLE = "Focused Web Searching with PDAs" ,BOOKTITLE = www00 ,links = "(title:www:http://dbpubs.stanford.edu/pub/1999-29)" ,entered-by = "Andreas Paepcke" ,YEAR = "2000" ,keywords = "power browser, pda, local search" ,abstract = {The Stanford Power Browser project addresses the problems of interacting with the World-Wide Web through wirelessly connected Personal Digital Assistants (PDAs). These problems include bandwidth limitations, screen real-estate shortage, battery capacity, and the time costs of pen-based search keyword input. As a way to address bandwidth and battery life limitations, we provide local site search facilities for all sites. We incrementally index Web sites in real time as the PDA user visits them. These indexes have narrow scope at first, and improve as the user dwells on the site, or as more users visit the site over time. We address the keyword input problem by providing site specific keyword completion, and indications of keyword selectivity within sites. The system is implemented on the Palm Pilot platform, using a Metricom radio link. We describe the user level experience, and then present the analyses that informed our technical decisions. } } @INPROCEEDINGS{buyu00 ,AUTHOR = "Orkut Buyukkokten and Hector Garcia-Molina and Andreas Paepcke" ,TITLE = "Accordion Summarization for End-Game Browsing on PDAs and Cellular Phones" ,BOOKTITLE = chi01 ,YEAR = "2000" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-57)" ,entered-by = "Andreas Paepcke" ,keywords = "PDA, power browser, powerbrowser" ,abstract = {We demonstrate a new browsing technique for devices with small displays such as PDAs or cellular phones. We concentrate on end-game browsing, where the user is close to or on the target page. We make browsing more efficient and easier by Accordion Summarization. In this technique the Web page is first represented as a short summary. The user can then drill down to discover relevant parts of the page. If desired, keywords can be highlighted and exposed automatically. We discuss our techniques, architecture, interface facilities, and the result of user evaluations. We measured a 57% improvement in browsing speed and 75% reduction in input effort. } } @INPROCEEDINGS{buyu00a ,AUTHOR = "Orkut Buyukkokten and Hector Garcia-Molina and Andreas Paepcke" ,TITLE = "Seeing the Whole in Parts: Text Summarization for Web Browsing on Handheld Devices" ,BOOKTITLE = "10th International WWW Conference" ,YEAR = "2000" ,note = "Available at http://dbpubs.stanford.edu/pub/2001-45" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2001-45)" ,entered-by = "Andreas Paepcke" ,keywords = "Personal Digital Assistant, PDA, Handheld Computers, Mobile Computing, Summarization, WAP, Wireless Computing, Ubiquitous Computing" ,abstract = {We introduce five methods for summarizing parts of Web pages on handheld devices, such as personal digital assistants (PDAs), or cellular phones. Each Web page is broken into text units that can each be hidden, partially displayed, made fully visible, or summarized. The methods accomplish summarization by different means. One method extracts significant keywords from the text units, another attempts to find each text unit's most significant sentence to act as a summary for the unit. We use information retrieval techniques, which we adapt to the World-Wide Web context. We tested the relative performance of our five methods by asking human subjects to accomplish single-page information search tasks using each method. We found that the combination of keywords and single-sentence summaries works best for a variety of search tasks.} } @INPROCEEDINGS{kalj00 ,AUTHOR = "Oliver Kaljuvee and Orkut Buyukkokten and Hector Garcia-Molina and Andreas Paepcke" ,TITLE = "Efficient Web Form Entry on PDAs" ,BOOKTITLE = "To appear in the Proceedings of the 10th Intl. WWW conference" ,YEAR = "2000" ,note = "Available at http://dbpubs.stanford.edu/pub/2001-44" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2001-44)" ,entered-by = "Andreas Paepcke" ,keywords = "PDA, mobile computing, WAP, forms, wireless access" ,abstract = {We propose a design for displaying and manipulating HTML forms on small PDA screens. The form input widgets are not shown until the user is ready to fill them in. At that point, only one widget is shown at a time. The form is summarized on the screen by displaying just the text labels that prompt the user for each widget's information. The challenge of this design is to automatically find the match between each text label in a form, and the input widget for which it is the prompt. We developed eight algorithms for performing such label/widget matches. Some of the algorithms are based on n-gram comparisons, while others are based on common form layout conventions. We applied a combination of these algorithms to 100 simple HTML forms with an average of four input fields per form. These experiments achieved a 95% matching accuracy. We developed a scheme that combines all algorithms into a matching system. This system did well even on complex forms, achieving 80% accuracy in our experiments involving 330 input fields spread over 48 complex forms. } } @INPROCEEDINGS{bald98a ,AUTHOR = "Michelle Q. Wang Baldonado, Terry Winograd" ,TITLE = "Hi-cites: dynamically created citations with active highlighting" ,BOOKTITLE = chi98 ,YEAR = "1998" ,entered-by = "Rebecca Wesley" ,abstract = {The original SenseMaker interface for information exploration [2] used tables to present heterogeneous document descriptions. In contrast, printed bibliographies and World Wide Web (WWW) search engines use formatted citations to convey this information. In this paper, we discuss hi-cites, a new interface construct developed for SenseMaker that combines the benefits of tables (which encourage the comparison of descriptions) and citations (which facilitate browsing). Hi-cites are dynamically created citations with active highlighting. They are useful in environments where heterogeneous structured descriptions must be browsed and compared with ease. Examples beyond digital libraries include product catalogs, classified advertisements, and WWW search engines. We have performed an evaluation of hi-cites, tables, and citations for tasks involving single attribute comparisons in the digital-library domain. This evaluation supports our claim that hi-cites are valuable for both comparison and skimming tasks in this environment. } } @MANUAL{z39.50-98 ,TITLE = "About Profiles" ,organization = "Library of Congress" ,note = "Accessible at http://lcweb.loc.gov/z3950/agency/profiles/about.html" ,month = "January" ,year = "1998" ,links = "(title:www:http://lcweb.loc.gov/z3950/agency/profiles/about.html)" ,entered-by = "Andreas Paepcke" ,keywords = "Z39.50, interoperability" ,abstract = {Defines concisely what a protocol 'profile' is.} } @MANUAL{zdsr97 ,TITLE = "Z39.50 Profile for Simple Distributed Search and Ranked Retrieval" ,organization = "Library of Congress" ,month = "March" ,year = "1997" ,note = "Accessible at http://lcweb.loc.gov/z3950/agency/profiles/zdsr.html" ,links = "(title:www:http://lcweb.loc.gov/z3950/agency/profiles/zdsr.html)" ,entered-by = "Andreas Paepcke" ,keywords = "Z39.50, profiles, STARTS" ,abstract = {Z39.50 profile based on STARTS. The profile specializes to search on metadata about documents and about search engines.} } @TECHREPORT{dasl99 ,AUTHOR = "Saveen Reddy and Dale Lowry and Surenda Reddy and Rick Henderson and Jim Davis and Alan Babich" ,TITLE = "DAV Searching & Locating, Internet Draft" ,INSTITUTION = "IETF" ,YEAR = "1999" ,month = "June" ,note = "Available at http://www.webdav.org/dasl/protocol/draft-dasl-protocol- 00.html" ,links = "(title:www:http://www.webdav.org/dasl/protocol/draft-dasl-protocol-00.html)" ,entered-by = "Andreas Paepcke" ,keywords = "DASL, DAV, searching" ,abstract = {Draft of the DASL document.} } @INPROCEEDINGS{lud99a ,AUTHOR = "Bertram Ludascher and Amarnath Gupta" ,TITLE = "Modeling Interactive Web Sources for Information Mediation" ,BOOKTITLE = "Intl. Workshop on the World-Wide Web and Conceptual Modeling, Paris, France (WWWCM'99)" ,YEAR = "1999" ,publisher = "Springer-Verlag, 1999" ,entered-by = "Rebecca Wesley" ,abstract = {~} } @MISC{data00 ,title = "Dataware Search and Retrieval" ,year = "2000" ,howpublished = "http://www.dataware.com/technology/" ,links = "(title:www:http://www.dataware.com/technology/)" ,entered-by = "Andreas Paepcke" ,keywords = "search engine, query translation" ,abstract = {Commercial company that seems to have some query translation. They say that you can define the front-end query language yourself.} } @MISC{http00 ,title = "HTTP -- Hypertext Transfer Protocol" ,year = "2000" ,howpublished = "http://www.w3.org/Protocols/" ,links = "(title:www:http://www.w3.org/Protocols/)" ,entered-by = "Andreas Paepcke" ,keywords = "HTTP" ,abstract = {Main page for HTTP protocol spec. Currently 1.1. Also has pointers to related standards, and HTTP-NG} } @MISC{dcom ,title = "Microsoft COM Technologies" ,howpublished = "http://www.microsoft.com/com/tech/DCOM.asp" ,links = "(title:www:http://www.microsoft.com/com/tech/DCOM.asp)" ,entered-by = "Andreas Paepcke" ,keywords = "DCOM specification download, papers, etc." ,abstract = {~} } @MANUAL{sdlip00 ,TITLE = "The Simple Digital Library Interoperability Protocol" ,organization = "Stanford University, University of California Berkeley, University of California Santa Barbara, San Diego Supercomputing Center, and California Digital Library" ,note = "Available at http://www-diglib.stanford.edu/~testbed/doc2/SDLIP/" ,year = "2000" ,links = "(title:www:http://www-diglib.stanford.edu/~testbed/doc2/SDLIP/)" ,entered-by = "Andreas Paepcke" ,keywords = "interoperability, infobus, interserv, protocol" ,abstract = {Main citation for SDLIP} } @ARTICLE{sdlip00a ,AUTHOR = "Andreas Paepcke and Robert Brandriff and Greg Janee and Ray Larson and Bertram Ludaescher and Sergey Melnik and Sriram Raghavan " ,TITLE = "Search Middleware and the Simple Digital Library Interoperability Protocol" ,JOURNAL = "DLIB Magazine" ,month = "March" ,YEAR = "2000" ,entered-by = "Andreas Paepcke" ,note = "Available at http://dbpubs.stanford.edu/pub/2000-53" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-53)" ,abstract = {We describe our Simple Digital Library Interoperability Protocol (SDLIP), which allows clients to query information sources in a uniform syntax. The protocol was developed in a collaboration between Stanford, the Universities of California at Berkeley, and Santa Barbara, the San Diego Supercomputer Center, and the California Digital Library. In addition to introducing the protocol, we describe several of our design choices, and compare them with the choices made in other search middleware approaches. The protocol allows for both stateful and stateless operation, supports multiple query languages, and defines a simple XML-based return format. A default query language that is included in SDLIP follows the evolving IETF DASL 'basicsearch'. This is an XML-encoded language reminiscent of SQL, but adjusted for use in full-text environments. SDLIP can be used with CORBA or HTTP. } } @TECHREPORT{sdlip00b ,AUTHOR = "Andreas Paepcke and Robert Brandriff and Greg Janee and Ray Larson and Bertram Ludaescher and Sergey Melnik and Sriram Raghavan " ,TITLE = "Search Middleware and the Simple Digital Library Interoperability Protocol (Long Version)" ,INSTITUTION = "Stanford University" ,YEAR = "2000" ,month = "February" ,number = "SIDL-WP-2000-0134" ,note = "Available at http://dbpubs.stanford.edu/pub/2000-52" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-52)" ,entered-by = "Andreas Paepcke" ,keywords = "sdlip, interoperability, protocols" ,abstract = {We describe our Simple Digital Library Interoperability Protocol (SDLIP), which allows clients to query information sources in a uniform syntax. The protocol was developed in a collaboration between Stanford, the Universities of California at Berkeley, and Santa Barbara, the San Diego Supercomputer Center, and the California Digital Library. In addition to introducing the protocol, we describe several of our design choices, and compare them with the choices made in other search middleware approaches. The protocol allows for both stateful and stateless operation, supports multiple query languages, and defines a simple XML-based return format. A default query language that is included in SDLIP follows the evolving IETF DASL 'basicsearch'. This is an XML-encoded language reminiscent of SQL, but adjusted for use in full-text environments. SDLIP can be used with CORBA or HTTP. } } @MISC{fairuse00 ,title = "Copyright and Fair Use" ,year = "2000" ,note = "Available at http://fairuse.stanford.edu/" ,organization = "Stanford University Libraries" ,entered-by = "Andreas Paepcke" ,keywords = "fair use, copyright, economic issues" ,abstract = {Articles, reference pointers, and search related to copyright issues.} } @InProceedings{ChangGarcia99qt, author = {Chen-Chuan K. Chang and H\'ector Garc\'{\i}a-Molina}, title = {Mind Your Vocabulary: Query Mapping Across Heterogeneous Information Sources}, booktitle = sigmod99, pages = {335--346}, year = 1999, month = Jun, address = {Philadelphia, Pa.}, publisher = {ACM Press, New York}, entered-by = "Chen-Chuan K. Chang" ,keywords = "query translation, rule-based translation" } @Book{FrakesBaeza-Yates92, author = {W. B. Frakes and R. Baeza-Yates}, title = {Information Retrieval Data Structures \& Algorithms}, publisher = {Prentice Hall}, year = 1992, address = {Englewood Cliffs, N.J.}, entered-by = "Chen-Chuan K. Chang" } @Book{Salton89, author = {Gerard Salton}, title = {Automatic Text Processing}, publisher = {Addison-Wesley}, year = 1989, address = {Reading, Mass.}, entered-by = "Chen-Chuan K. Chang" } @BOOK{Rijsbergen79 ,AUTHOR = "C. J. Van Rijsbergen" ,TITLE = "Information Retrieval, 2nd edition" ,PUBLISHER = "Butterworths" ,YEAR = "1979" ,address = "London" ,entered-by = "Chen-Chuan K. Chang" } @BOOK{Niso95:Z39.50, AUTHOR = "{National Information Standards Organization}", TITLE = "Information Retrieval ({Z39.50}): Application Service Definition and Protocol Specification ({ANSI/NISO Z39.50- 1995})", PUBLISHER = "NISO Press", YEAR = "1995", address = "Bethesda, Md.", entered-by = "Chen-Chuan K. Chang", note = {Accessible at {\tt http://\-lcweb.loc.gov/\-z3950/\-agency/}} } @Misc{Z39.50:Bib-1, author = {{Z39.50 Maintenance Agency}}, title = {Attribute Set {Bib-1} ({Z39.50-1995}): Semantics}, howpublished = {Accessible at {\tt ftp://\-ftp.loc.gov/\-pub/\-z3950/\-defs/\- bib1.txt}}, year = 1995, entered-by = "Chen-Chuan K. Chang", month = Sep } @Article{CrystalJakobson82, author = {M. I. Crystal and G. E. Jakobson}, title = {{FRED}, A Front End for Databases}, journal = {Online}, year = 1982, volume = 6, number = 5, month = Sep, pages = {27--30}, entered-by = "Chen-Chuan K. Chang" } @Article{HawkinsLevy85, author = {D. T. Hawkins and L. R. Levy}, title = {Front End Software for Online Database Searching {Part 1}: Definitions, System Features, and Evaluation}, journal = {Online}, year = 1985, volume = 9, number = 6, month = Nov, pages = {30--37}, entered-by = "Chen-Chuan K. Chang" } @Article{Marcus82, author = {R. S. Marcus}, title = {User Assistance in Bibliographic Retrieval Networks Through a Computer Intermediary}, journal = {IEEE Trans. on Systems, Man, and Cybernetics}, year = 1982, volume = {smc-12}, number = 2, pages = {116--133}, entered-by = "Chen-Chuan K. Chang" } @InProceedings{PreeceWilliams80, author = {S.E. Preece and M.E. Williams}, title = {Software for the Searcher's Workbench}, booktitle = {Proceedings of the 43rd American Society for Information Science Annual Meeting}, volume = 17, year = 1980, month = Oct, address = {Anaheim, Calif.}, pages = {403--405}, publisher = {Knowledge Industry Publications, White Plains, N.Y.}, entered-by = "Chen-Chuan K. Chang" } @INPROCEEDINGS{SelbergEtzioni95 ,AUTHOR = {Erik Selberg and Oren Etzioni} ,TITLE = {Multi-Service Search and Comparison using the {MetaCrawler}} ,BOOKTITLE = {Proceedings of the 4th International WWW Conference} ,YEAR = 1995 ,month = dec ,address = "Boston, Mass." ,entered-by = "Chen-Chuan K. Chang" } @Article{Toliver82, author = {D. E. Toliver}, title = {{OL'SAM}: An Intelligent Front-End for Bibliographic Information Retrieval}, journal = {Information, Technology and Libraries}, year = 1982, pages = {317--326}, volume = 1, number = 4, entered-by = "Chen-Chuan K. Chang" } @Article{Williams86, author = {M. E. Williams}, title = {Transparent Information Systems Through Gateways, Front Ends, Intermediaries, and Interfaces}, journal = {Journal of the American Society for Information Science}, year = 1986, volume = 37, number = 4, month = Jul, pages = {204--214}, entered-by = "Chen-Chuan K. Chang" } @Article{ZinnSB86, author = {S. Zinn and M. Sellers and D. Bohli}, title = {{OCLC's} Intelligent Gateway Service: Online Information Access for Libraries}, journal = {Library Hi Tech}, year = 1986, volume = 4, number = 3, pages = {25--29}, entered-by = "Chen-Chuan K. Chang" } @TechReport{BowmanDH+94, author = {C. Mic Bowman and Peter B. Danzig and Darren R. Hardy and Udi Manber and Michael F. Schwartz and Duane P. Wessels}, title = {Harvest: A Scalable, Customizable Discovery and Access System}, institution = {Dept. of Computer Science, Univ. of Colorado}, year = 1994, number = {CU-CS-732-94}, address = {Boulder, Colo.}, month = Aug, note = {Accessible at {\tt http://\-harvest.transarc.com/}}, entered-by = "Chen-Chuan K. Chang" } @TechReport{RaoJR94, author = {R. Rao and B. Janssen and A. Rajaraman}, title = {{GAIA} Technical Overview}, institution = {Xerox {PARC}}, year = 1994, entered-by = "Chen-Chuan K. Chang" } @InProceedings{RaoRM93, author = {R. Rao and D.M. Russel and J.D. Mackinlay}, title = {System Components for Embedded Information Retrieval from Multiple Disparate Information Sources}, booktitle = {Proceedings of the ACM UIST '93}, year = 1993, month = Nov, address = {Atlanta, Ga.}, publisher = placm, pages = {23--33}, entered-by = "Chen-Chuan K. Chang" } @InProceedings{Mitchell73, author = {Patrick C. Mitchell}, title = {A Note about the Proximity Operators in Information Retrieval}, booktitle = {Proceedings of {ACM SIGPLAN-SIGIR} Interface Meeting}, year = 1973, month = Nov, address = {Gaithersburg, Md.}, publisher = placm, pages = {177--180}, entered-by = "Chen-Chuan K. Chang" } @Article{Loeffen94, author = {Arjan Loeffen}, title = {Text Databases: A Survey of Text Models and Systems}, journal = {{SIGMOD} Record}, year = 1994, volume = 23, number = 1, month = Mar, pages = {97--106}, entered-by = "Chen-Chuan K. Chang" } @InProceedings{NavarroBaeza95, author = {Gonzalo Navarro and Ricardo Baeza-Yates}, title = {A Language for Queries on Structure and Contents of Textual Databases}, booktitle = sigir95, year = 1995, month = Jul, publisher = placm, address = {Seattle, Wash.}, pages = {93--101}, entered-by = "Chen-Chuan K. Chang" } @InProceedings{ChristophidesAC+94, author = {V. Christophides and S. Abiteboul and S. Cluet and M. Scholl}, title = {From Structured Documents to Novel Query Facilities}, booktitle = sigmod94, year = 1994, publisher = placm, pages = {313--324}, entered-by = "Chen-Chuan K. Chang" } @InProceedings{AbiteboulCM93, author = {Serge Abiteboul and Sophie Cluet and Tova Milo}, title = {Querying and Updating the File}, booktitle = vldb93, year = 1993, address = {Dublin, Ireland}, pages = {73--84}, publisher = plvldb, entered-by = "Chen-Chuan K. Chang" } @Book{Iso93:ISO8777, author = {{ISO}}, title = {{ISO} 8777:1993 Information and Documentation -- Commands for Interactive Text Searching}, publisher = {Int'l Organization for Standardization}, year = 1993, address = {Geneva, Switzerland}, edition = {First}, entered-by = "Chen-Chuan K. Chang" } @Book{Niso93:Z39.58, author = {{National Information Standards Organization}}, title = {{Z39.58-1992} Common Command Language for Online Interactive Information Retrieval}, publisher = {NISO Press}, year = 1993, address = {Bethesda, Md.}, entered-by = "Chen-Chuan K. Chang" } @InProceedings{Negus79, author = {A. E. Negus}, title = {Development of the {Euronet-Diane Common Command Language}}, booktitle = {Proceedings 3rd Int'l Online Information Meeting}, year = 1979, publisher = {Learned Information, Oxford, U.K.}, pages = {95--98}, entered-by = "Chen-Chuan K. Chang" } @TechReport{Martin74, author = {T. H. Martin}, title = {A Feature Analysis of Interactive Retrieval Systems}, institution = {Institute of Communication Research, Stanford Univ.}, year = 1974, type = {Report}, number = {SU-COMM-ICR-74-1}, address = {Stanford, Calif.}, month = Sep, entered-by = "Chen-Chuan K. Chang" } @InProceedings{Paepcke93, author = {Andreas Paepcke}, title = {An Object-Oriented View onto Public, Heterogeneous Text Databases}, booktitle = icde93, year = 1993, month = Apr, address = {Vienna, Austria}, pages = {484--493}, publisher = plieeecs, entered-by = "Chen-Chuan K. Chang" } @ARTICLE{Faloutsos85 ,AUTHOR = "Christos Faloutsos" ,TITLE = "Access Methods for Text" ,JOURNAL = csurvey ,YEAR = 1985 ,month = Mar ,volume = 17 ,number = 1 ,pages = "49--74" ,entered-by = "Chen-Chuan K. Chang" } @INPROCEEDINGS{Harman93 ,AUTHOR = "Donna Harman" ,TITLE = "Document Detection Overview" ,BOOKTITLE = "Proceedings {TIPSTER} Text Program (Phase I)" ,YEAR = 1993 ,month = Sep ,address = {Fredricksburg, Va.} ,publisher = "Morgan Kaufmann, San Francisco, Calif." ,entered-by = "Chen-Chuan K. Chang" } @Article{Lovins68, author = {J. B. Lovins}, title = {Development of a Stemming Algorithm}, journal = {Mechanical Translation and Computational Linguistics}, year = 1968, volume = 11, number = {1-2}, publisher = {Association for the Machine Translation and Computational Linguistics}, adress = {Chicago}, pages = {22--31}, entered-by = "Chen-Chuan K. Chang" } @Article{Porter80, author = {M. F. Porter}, title = {An Algorithm for Suffix Stripping}, journal = {Program}, year = 1980, month = Jul, volume = 14, number = 3, pages = {130--137}, publisher = {Belfast, Northern Ireland}, entered-by = "Chen-Chuan K. Chang" } @InProceedings{HyonBorgen96, author = {Jason J. Hyon and Rosana Bisciotti Borgen}, title = {Data Archival and Retrieval Enhancement {(DARE)} Metadata Modeling and its User Interface}, booktitle = {Proceedings of the First IEEE Metadata Conference}, year = 1996, organization = {IEEE}, address = {Silver Spring, Md.}, month = Apr, entered-by = "Chen-Chuan K. Chang" } @TechReport{LagozeLD96, author = {Carl Lagoze and Clifford A. Lynch and Daniel, Jr., Ron}, title = {The {W}arwick {F}ramework: A Container Architecture for Aggregating Sets of Metadata}, institution = {Cornell Univ., Computer Science Dept.}, year = 1996, number = {TR96-1593}, month = Jun, entered-by = "Chen-Chuan K. Chang" } @INPROCEEDINGS{Ullman97 ,AUTHOR = "Jeffrey D. Ullman" ,TITLE = "Information Integration Using Logical Views" ,BOOKTITLE = icdt97 ,YEAR = 1997 ,month = Jan ,publisher = plspringer ,address = "Delphi, Greece" ,entered-by = "Chen-Chuan K. Chang" } @INPROCEEDINGS{LevyRO96-vldb ,AUTHOR = "Alon Y. Levy and Anand Rajaraman and Joann J. Ordille" ,TITLE = "Querying Heterogeneous Information Sources Using Source Descriptions" ,BOOKTITLE = vldb96 ,YEAR = 1996 ,publisher = plvldb ,address = "Bombay, India" ,pages = "251--262" ,entered-by = "Chen-Chuan K. Chang" ,keywords = "query translation, Information manifold" } @InProceedings{LRO96, author = {Alon Y. Levy and Anand Rajaraman and Joann J. Ordille}, title = {Query-Answering Algorithms for Information Agents}, booktitle = {Proceedings of the 13th National Conference on Artificial Intelligence, AAAI-96}, year = 1996, address = {Portland, Oreg.}, month = Aug, publisher = plaaai, entered-by = "Chen-Chuan K. Chang" ,keywords = "query translation, Information manifold" } @InProceedings{RajaramanSU95, author = {Anand Rajaraman and Yehoshua Sagiv and Jeffrey D. Ullman}, title = {Answering Queries Using Templates with Binding Patterns}, booktitle = pods95, pages = {105--112}, year = 1995, address = {San Jose, Calif.}, month = May, entered-by = "Chen-Chuan K. Chang" } @InProceedings{LRU96, author = {Alon Y. Levy and Anand Rajaraman and Jeffrey D. Ullman}, title = {Answering Queries Using Limited External Query Processors}, booktitle = pods96, pages = {27--37}, year = 1996, address = {Montreal, Canada}, month = Jun, entered-by = "Chen-Chuan K. Chang" } @InProceedings{LMSS95, author = {Alon Y. Levy and Alberto O. Mendelzon and Yehoshua Sagiv and Divesh Srivastava}, title = {Answering Queries Using Views}, booktitle = pods95, pages = {95--104}, year = 1995, address = {San Jose, Calif.}, month = May, entered-by = "Chen-Chuan K. Chang" } @Article{LSK95, author = {Alon Y. Levy and Divesh Srivastava and Thomas Kirk}, title = {Data Model and Query Evaluation in Global Information Systems}, journal = {Journal of Intelligent Information Systems, 1995. Special Issue on Networked Information Discovery and Retrieval}, year = 1995, entered-by = "Chen-Chuan K. Chang" } @PHDTHESIS{Duschka97 ,AUTHOR = "Oliver M. Duschka" ,TITLE = "Query Planning and Optimization in Information Integration" ,SCHOOL = "Stanford University" ,YEAR = 1997 ,month = dec ,entered-by = "Chen-Chuan K. Chang" ,found-in = "Technical Report STAN-CS-TR-97-1598" ,keywords = "query translation, Infomaster" } @INPROCEEDINGS{GeneserethKD97 ,AUTHOR = "Michael R. Genesereth and Arthur M. Keller and Oliver M. Duschka" ,TITLE = "Infomaster: An Information Integration System" ,BOOKTITLE = sigmod97 ,publisher = placm ,YEAR = 1997 ,address = "Tucson, Ariz." ,entered-by = "Chen-Chuan K. Chang" ,keywords = "query translation, Infomaster" } @INPROCEEDINGS{HaasKW+97 ,AUTHOR = "Laura M. Haas and Donald Kossmann and Edward L. Wimmers and Jun Yang" ,TITLE = "Optimizing Queries Across Diverse Data Sources" ,booktitle = vldb97 ,year = 1997 ,month = Aug ,pages = {276-285} ,address = "Athens, Greece" ,publisher = plvldb ,entered-by = "Chen-Chuan K. Chang" ,keywords = "query translation, Garlic" } @INPROCEEDINGS{RothSchwarz97 ,AUTHOR = "Mary Tork Roth and Peter M. Schwarz" ,TITLE = "Don't Scrap It, Wrap It! A Wrapper Architecture for Legacy Data Sources" ,booktitle = vldb97 ,year = 1997 ,month = Aug ,pages = {266--275} ,address = "Athens, Greece" ,publisher = plvldb ,entered-by = "Chen-Chuan K. Chang" ,keywords = "query translation, Garlic" } @TECHREPORT{KapitskaiaTV97 ,AUTHOR = "Olga Kapitskaia and Anthony Tomasic and Patrick Valduriez" ,TITLE = "Dealing with Discrepancies in Wrapper Functionality" ,INSTITUTION = "INRIA" ,YEAR = 1997 ,number = "RR-3138" ,entered-by = "Chen-Chuan K. Chang" ,keywords = "query translation, DISCO" } @INPROCEEDINGS{PapakonstantinouGH96 ,AUTHOR = "Yannis Papakonstantinou and Ashish Gupta and Laura Haas" ,TITLE = "Capabilities-Based Query Rewriting in Mediator Systems" ,BOOKTITLE = pdis96 ,YEAR = 1996 ,address = "Miami Beach, Flor." ,entered-by = "Chen-Chuan K. Chang" } @INPROCEEDINGS{PapakonstantinouGU96 ,AUTHOR = "Yannis Papakonstantinou and H\'ector Garc\'{\i}a-Molina and Jeffrey Ullman" ,TITLE = "MedMaker: A Mediation System Based on Declarative Specifications" ,BOOKTITLE = icde96 ,YEAR = "1996" ,address = "New Orleans, La." ,entered-by = "Chen-Chuan K. Chang" ,keywords = "TSIMMIS, Mediators, query translation" } @INPROCEEDINGS{LabioYG97 ,AUTHOR = {H\'ector Garc\'{\i}a-Molina and Wilburt Labio and Ramana Yerneni} ,TITLE = {Capability Sensitive Query Processing on Internet Sources} ,BOOKTITLE = icde99 ,YEAR = 1999 ,month = mar ,address = "Sydney, Australia" ,note = {Accessible at http://dbpubs.stanford.edu/pub/1998-40} ,links = "(title:www:http://dbpubs.stanford.edu/pub/1998-40)" ,entered-by = "Chen-Chuan K. Chang" } @InProceedings{Chaudhuri93, author = {Surajit Chaudhuri}, title = {Finding Nonrecursive Envelopes for Datalog Predicates}, booktitle = pods93, publisher = placm, address = "Washingtion, D.C.", year = {1993}, pages = {135-146}, entered-by = "Chen-Chuan K. Chang" } @InProceedings{ChaudhuriKolaitis94, author = {Surajit Chaudhuri and Phokion G. Kolaitis}, title = {Can Datalog be Approximated?}, booktitle = pods94, publisher = placm, address = {Minneapolis, Minn.}, year = {1994}, pages = {86-96}, entered-by = "Chen-Chuan K. Chang" } @inproceedings{ChuMB93, author = {Wesley W. Chu and M. A. Merzbacher and L. Berkovich}, title = {The Design and Implementation of CoBase}, booktitle = sigmod93, publisher = placm, address = {Washington, D.C.}, year = {1993}, pages = {517-522}, } @inproceedings{TanGO99, author = {Kian-Lee Tan and Cheng Hian Goh and Beng Chin Ooi}, title = {On Getting Some Answers Quickly, and Perhaps More Later}, booktitle = icde99, publisher = placm, address = {Sydney, Austrialia}, year = {1999}, pages = {32-39}, entered-by = "Chen-Chuan K. Chang" } @inproceedings{PoosalaGanti99, author = {Viswanath Poosala and Venkatesh Ganti}, title = {Fast Approximate Query Answering Using Precomputed Statistics}, booktitle = icde99, publisher = placm, address = {Sydney, Austrialia}, year = {1999}, pages = {252}, entered-by = "Chen-Chuan K. Chang" } @inproceedings{CareyKossmann97, author = {Michael J. Carey and Donald Kossmann}, title = {On Saying "Enough Already!" in SQL}, booktitle = sigmod97, publisher = placm, address = {Tucson, Arizona}, year = {1997}, pages = {219-230}, entered-by = "Chen-Chuan K. Chang" } @inproceedings{CareyKossmann98, author = {Michael J. Carey and Donald Kossmann}, title = {Reducing the Braking Distance of an SQL Query Engine}, booktitle = vldb98, publisher = plvldb, address = {New York City, USA}, year = {1998}, pages = {158-169}, entered-by = "Chen-Chuan K. Chang" } @Article{bhp94, author = {M.W. Bright and A.R. Hurson and S. Pakzad}, title = {Automated Resolution of Sematic Heterogeneity in Multidatabases}, journal = {ACM Transaction on Database Systems}, year = 1994, volume = 19, number = 2, month = Jun, pages = {212-253}, entered-by = "Chen-Chuan K. Chang" } @InProceedings{ap93, author = {Cyrus Azarbod and William Perrizo}, title = {Building Concept Hierarchies for Schema Integration in HDDBS Using Incremental Concept Formation}, booktitle = {CIKM 93. Proceedings of the Second International Conference on Information and Knowledge Management}, editor = {Bhargava, B. and Finin, T. and Yesha, Y.}, year = 1993, organization = {ACM}, address = {Washington, D.C.}, month = Nov, pages = {732-734}, entered-by = "Chen-Chuan K. Chang" } @INPROCEEDINGS{GyssensPG89 ,AUTHOR = "Marc Gyssens and Jan Paredaens and Dirk Van Gucht" ,TITLE = "A Grammar-Based Approach Towards Unifying Hierarchical Data Models" ,BOOKTITLE = sigmod89 ,publisher = placm ,YEAR = "1989" ,month = Jun ,address = {Portland, Oreg.} ,entered-by = "Chen-Chuan K. Chang" } @BOOK{Goldfarb90 ,AUTHOR = "Charles F. Goldfarb" ,TITLE = "The {SGML} Handbook" ,PUBLISHER = "Oxford University Press" ,YEAR = 1990 ,address = "New York" ,entered-by = "Chen-Chuan K. Chang" } @INPROCEEDINGS{AbiteboulCM97 ,AUTHOR = "Serge Abiteboul and Sophie Cluet and Tova Milo" ,TITLE = "Correspondence and Translation for Heterogeneous Data" ,BOOKTITLE = icdt97 ,YEAR = "1997" ,publisher = plspringer ,address = "Delphi, Greece" ,entered-by = "Chen-Chuan K. Chang" } @INPROCEEDINGS{BunemanDH+95 ,AUTHOR = "P. Buneman and S.B. Davidson and K. Hart and C. Overton and L. Wong" ,TITLE = "A Data Transformation System for Biological Data Sources" ,BOOKTITLE = vldb95 ,YEAR = 1995 ,address = "Zurich, Switzerland" ,publisher = plvldb ,entered-by = "Chen-Chuan K. Chang" } @INPROCEEDINGS{ShivakumarGC98 ,AUTHOR = "Narayanan Shivakumar and Hector Garcia-Molina and Chandra Chekuri" ,TITLE = "Filtering with Approximate Predicates" ,BOOKTITLE = vldb98 ,YEAR = 1998 ,publisher = plvldb ,pages = "263--274" ,address = "New York City, USA" ,entered-by = "Chen-Chuan K. Chang" } @ARTICLE{FengWakayama93 ,AUTHOR = "An Feng and Toshiro Wakayama" ,TITLE = "{SIMON}: a grammar-based transformation system for structured documents" ,JOURNAL = "Electronic Publishing: Origination, Dissemination and Design" ,YEAR = 1993 ,month = dec ,volume = "6" ,number = "4" ,pages = {361--372} ,entered-by = "Chen-Chuan K. Chang" } @ARTICLE{Arnon93 ,AUTHOR = "Dennis S. Arnon" ,TITLE = "Scrimshaw: a language for document queries and transformations" ,JOURNAL = "Electronic Publishing: Origination, Dissemination and Design" ,YEAR = 1993 ,month = dec ,volume = "6" ,number = "4" ,pages = {361--372} ,entered-by = "Chen-Chuan K. Chang" } @ARTICLE{Wirth77 ,AUTHOR = "Niklaus Wirth" ,TITLE = "What Can We Do about the Unnecessary Diversity of Notation for Syntactic Definitions" ,JOURNAL = cacm ,YEAR = 1977 ,month = Nov ,volume = 20 ,number = 11 ,pages = {822-823} ,entered-by = "Chen-Chuan K. Chang" } @INPROCEEDINGS{Masui98 ,AUTHOR="Toshiyuki Masui" ,TITLE="An Efficient Text Input Method for Pen-based Computers" ,BOOKTITLE=chi98 ,pages = {328-335} ,YEAR="1998" ,entered-by = "Orkut Buyukkokten" } @INPROCEEDINGS{Marc97 ,AUTHOR="Massimo Marchiori" ,TITLE="The Quest for Correct Information on the Web: Hyper Search Engines" ,BOOKTITLE=www97 ,pages = {265-276} ,YEAR="1997" ,entered-by = "Orkut Buyukkokten" } @MISC{WebClipping ,author = "Palm Inc." ,title = "Web Clipping Development" ,howpublished = "Palm website: http://www.palm.com/dev/tech/webclipping/" ,entered-by = "Orkut Buyukkokten" ,keywords = "web clipping, PalmVII" } @MISC{PalmScape ,author = "Kazhuo Oku" ,title = "Palmscape" ,howpublished = "Palmscape website: http://palmscape.ilinx.co.jp/" ,entered-by = "Orkut Buyukkokten" ,keywords = "web browser, pda" } @MISC{HandWeb ,author = "Smartcode Software" ,title = "HandWeb" ,howpublished = "Smartcode Software website: http://www.smartcodesoft.com/" ,entered-by = "Orkut Buyukkokten" ,keywords = "web browser, pda" } @MISC{ProxiWeb ,author = "ProxiNet" ,title = "ProxiWeb" ,howpublished = "ProxiNet website: http://www.proxinet.com/" ,entered-by = "Orkut Buyukkokten" ,keywords = "web browser, pda" } @MISC{SnakeEyes ,author = "Snakefeet" ,title = "SnakeEyes" ,howpublished = "Snakefeet website: http://www.snakefeet.com/" ,entered-by = "Orkut Buyukkokten" ,keywords = "web browser, pda" } @INPROCEEDINGS{Fox98 ,AUTHOR = "Armando Fox and Ian Goldberg and Steven D. Gribble and David C. Lee" ,TITLE = "Experience With Top Gun Wingman: A Proxy-Based Graphical Web Browser for the 3Com PalmPilot" ,BOOKTITLE = "Proceedings of Middleware '98, Lake District, England, September 1998" ,YEAR = "1998" ,entered-by = "Orkut Buyukkokten" } @BOOK{hutc92 ,AUTHOR = "W.J. Hutchins and H.L. Somers" ,TITLE = "An Introduction to Machine Translation" ,PUBLISHER = "Academic Press" ,YEAR = "1992" ,entered-by = "Andreas Paepcke" ,keywords = "natural language translation, linguistics" ,abstract = {Recent textbook on natural language translation.} } @INPROCEEDINGS{bald99 ,AUTHOR = "Michelle Baldonado and Steve Cousins and B. Lee and Andreas Paepcke" ,TITLE = "Notable: An Annotation System for Networked Handheld Devices" ,BOOKTITLE = chi99 ,YEAR = "1999" ,pages = "210-211" ,entered-by = "Andreas Paepcke" ,keywords = "annotation, handheld devices, Palm Pilot, mobile computing" ,abstract = {~} } @INPROCEEDINGS{cho00 ,AUTHOR = "Junghoo Cho and Hector Garcia-Molina" ,TITLE = "Synchronizing a Database to Improve Freshness" ,BOOKTITLE = sigmod00 ,YEAR = "2000" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1999-40)" ,note = "Available at http://dbpubs.stanford.edu/pub/1999-40" ,entered-by = "Andreas Paepcke" ,keywords = "crawling, webbase" ,abstract = {In this paper we study how to refresh a local copy of an autonomous data source to maintain the copy up-to-date. As the size of the data grows, it becomes more difficult to maintain the copy "fresh," making it crucial to synchronize the copy effectively. We define two freshness metrics, change models of the underlying data, and synchronization policies. We analytically study how effective the various policies are. We also experimentally verify our analysis, based on data collected from 270 web sites for more than 4 months, and we show that our new policy improves the "freshness" very significantly compared to current policies in use. } } @INPROCEEDINGS{cho00a ,AUTHOR = "Junghoo Cho and Narayanan Shivakumar and Hector Garcia-Molina" ,TITLE = "Finding Replicated Web Collections" ,BOOKTITLE = sigmod00 ,YEAR = "2000" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1999-64)" ,note = "Available at http://dbpubs.stanford.edu/pub/1999-64" ,entered-by = "Andreas Paepcke" ,keywords = "crawling, webbase" ,abstract = {Many web documents (such as JAVA FAQs) are being replicated on the Internet. Often entire document collections (such as hyperlinked Linux manuals) are being replicated many times. In this paper, we make the case for identifying replicated documents and collections to improve web crawlers, archivers, and ranking functions used in search engines. The paper describes how to efficiently identify replicated documents and hyperlinked document collections. The challenge is to identify these replicas from an input data set of several tens of millions of web pages and several hundreds of gigabytes of textual data. We also present two real-life case studies where we used replication information to improve a crawler and a search engine. We report these results for a data set of 25 million web pages (about 150 gigabytes of HTML data) crawled from the web} } @INPROCEEDINGS{bran00 ,AUTHOR = "Onn Brandman and Junghoo Cho and Hector Garcia-Molina and Narayanan Shivakumar" ,TITLE = "Crawler-Friendly Web Servers" ,BOOKTITLE = "Proceedings of the Workshop on Performance and Architecture of Web Servers (PAWS)" ,YEAR = "2000" ,month = "June" ,address = "Santa Clara, California" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-25)" ,note = "Held in conjunction with ACM SIGMETRICS 2000. Available at http://dbpubs.stanford.edu/pub/2000-25" ,entered-by = "Andreas Paepcke" ,keywords = "crawling, webbase" ,abstract = {In this paper we study how to make web servers (e.g., Apache) more crawler friendly. Current web servers offer the same interface to crawlers and regular web surfers, even though crawlers and surfers have very different performance requirements. We evaluate simple and easy-to-incorporate modifications to web servers so that there are significant bandwidth savings. Specifically, we propose that web servers export meta-data archives decribing their content. } } @INPROCEEDINGS{buyu99b ,AUTHOR = "Orkut Buyukokkten and Junghoo Cho and Hector Garcia-Molina and Luis Gravano and Narayanan Shivakumar" ,TITLE = "Exploiting Geographical Location Information of Web Pages" ,BOOKTITLE = "Proceedings of Workshop on Web Databases (WebDB'99)" ,YEAR = "1999" ,month = "June" ,note = "Held in conjunction with ACM SIGMOD'99. Available at http://dbpubs.stanford.edu/pub/1999-4" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1999-4)" ,entered-by = "Andreas Paepcke" ,keywords = "value filtering" ,abstract = {Many information sources on the web are relevant primarily to specific geographical communities. For instance, web sites containing information on restaurants, theatres and apartment rentals are relevant primarily to web users in geographical proximity to these locations. We make the case for identifying and exploiting the geographical location information of web sites so that web applications can rank information in a geographically sensitive fashion. For instance, when a user in Palo Alto issues a query for "Italian Restaurants," a web search engine can rank results based on how close such restaurants are to the user's physical location rather than based on traditional IR measures. In this paper, we first consider how to compute the geographical location of web pages. Subsequently, we consider how to exploit such information in one specific "proof-of-concept" application we implemented in JAVA. } } @INPROCEEDINGS{cho00b ,AUTHOR = "Junghoo Cho and Hector Garcia-Molina" ,TITLE = "The Evolution of the Web and Implications for an Incremental Crawler" ,BOOKTITLE = vldb00 ,YEAR = "2000" ,note = "Available at http://dbpubs.stanford.edu/pub/1999-22" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1999-22)" ,entered-by = "Andreas Paepcke" ,keywords = "crawling, webbase" ,abstract = {In this paper we study how to build an effective incremental crawler. The crawler selectively and incrementally updates its index and/or local collection of web pages, instead of periodically refreshing the collection in batch mode. The incremental crawler can improve the ``freshness'' of the collection significantly and bring in new pages in a more timely manner. We first present results from an experiment conducted on more than half million web pages over 4 months, to estimate how web pages evolve over time. Based on these experimental results, we compare various design choices for an incremental crawler and discuss their trade-offs. We propose an architecture for the incremental crawler, which combines the best design choices. } } @INPROCEEDINGS{cho00c ,AUTHOR = "Junghoo Cho and Hector Garcia-Molina" ,TITLE = "Estimating Frequency of Change" ,BOOKTITLE = "submitted for publication" ,note = "Available at http://dbpubs.stanford.edu/pub/2000-4" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-4)" ,YEAR = "2000" ,entered-by = "Andreas Paepcke" ,keywords = "crawling, webbase" ,abstract = {~} } @INPROCEEDINGS{coop00 ,AUTHOR = "Brian Cooper and Hector Garcia-Molina" ,TITLE = "InfoMonitor: Unobtrusively Archiving a World Wide Web Server" ,BOOKTITLE = "Submitted for publication" ,YEAR = "2000" ,note = "Available at http://dbpubs.stanford.edu/pub/2000-15" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-15)" ,entered-by = "Andreas Paepcke" ,keywords = "archiving" ,abstract = {It may be important to provide long-term preservation of digital data even when that data is stored in an unreliable system, such as a filesystem, a legacy database, or even the World Wide Web. In this research paper we focus on the problem of archiving the contents of a web site without disrupting users who maintain the site. We propose an archival storage system, the InfoMonitor, in which a reliable archive is integrated with an unmodified existing store. Implementing such a system presents various challenges related to the mismatch of features between the components, such as differences in naming and data manipulation operations. We examine each of these issues as well as solutions for the conflicts that arise. We also discuss our experience using the InfoMonitor to archive the Stanford Database Group's web site.} } @INPROCEEDINGS{coop00a ,AUTHOR = "Brian Cooper and Arturo Crespo and Hector Garcia-Molina" ,TITLE = "Implementing a Reliable Digital Object Archive" ,BOOKTITLE = "Submitted for publication" ,YEAR = "2000" ,note = "Available at http://dbpubs.stanford.edu/pub/2000-27" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-27)" ,entered-by = "Andreas Paepcke" ,keywords = "archiving" ,abstract = {An Archival Repository reliably stores digital objects for long periods of time (decades or centuries). The archival nature of the system requires new techniques for storing, indexing, and replicating digital objects. In this paper we discuss the specialized indexing needs of a write-once archive. We also present a reliability algorithm for effectively replicating sets of related objects. We describe an administrative user interface and a data import utility for archival repositories. Finally, we discuss and evaluate a prototype repository we have built, the Stanford Archival Vault, SAV.} } @INPROCEEDINGS{cres00 ,AUTHOR = "Arturo Crespo and Hector Garcia-Molina" ,TITLE = "Modeling Archival Repositories for Digital Libraries" ,BOOKTITLE = "Submitted for publication" ,YEAR = "2000" ,note = "Available at http://dbpubs.stanford.edu/pub/1999-23" ,links = "(title:www:http://dbpubs.stanford.edu/pub/1999-23)" ,entered-by = "Andreas Paepcke" ,keywords = "archiving" ,abstract = {This paper studies the archival problem: how a digital library can preserve electronic documents over long periods of time. We analyze how an archival repository can fail and we present different strategies that help solve the problem. We introduce ArchSim, a simulation tool that for evaluating an implementation of an archival repository system and compare options such as different disk reliabilities, error detection and correction algorithms, preventive maintenance, etc. We use ArchSim to analyze a case study of an Archival Repository for Computer Science Technical Reports. } } @INPROCEEDINGS{cres00a ,AUTHOR = "Arturo Crespo and Orkut Buyukkokten and Hector Garcia-Molina" ,TITLE = "Efficient Query Subscription Processing in a Multicast Environment " ,BOOKTITLE = icde00 ,YEAR = "2000" ,note = "Available at http://dbpubs.stanford.edu/pub/2000-54" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-54)" ,entered-by = "Andreas Paepcke" ,keywords = "~" ,abstract = {This paper introduces techniques for reducing data dissemination costs of query subscriptions. The reduction is achieved by merging queries with overlapping, but not necessarily equal, answers. The paper formalizes the query-merging problem and introduces a general cost model for it. We prove that the problem is NP-hard and propose exhaustive algorithms and three heuristic algorithms: the Pair Merging Algorithm, the Directed Search Algorithm and the Clustering Algorithm. We develop a simulator for evaluating the different heuristics and show that the performance of our heuristics is close to optimal.} } @INPROCEEDINGS{huan00 ,AUTHOR = "Yongqiang Huang and Hector Garcia-Molina" ,TITLE = "Exactly-Once Semantics in a Replicated Messaging System" ,BOOKTITLE = "Submitted for publication" ,YEAR = "2000" ,note = "Available at http://dbpubs.stanford.edu/pub/2000-7" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-7)" ,entered-by = "Andreas Paepcke" ,keywords = "mobile information distribution" ,abstract = {~} } @INPROCEEDINGS{meln00www01, author = "Sergey Melnik and Sriram Raghavan and Beverly Yang and Hector Garcia-Molina", title = "Building a Distributed Full-Text Index for the Web", booktitle = www01, year = "2001", entered-by = "Sriram Raghavan", keywords = "Text-index Web WebBase", } @TechReport{meln00, author = "Sergey Melnik and Sriram Raghavan and Beverly Yang and Hector Garcia-Molina", title = "Building a Distributed Full-Text Index for the Web", institution = "Stanford Digital Library Project, Computer Science Department, Stanford University", year = "2000", month = "July", number = "SIDL-WP-2000-0140; 2000-29", note = "Available at http://dbpubs.stanford.edu/pub/2000-29", links = "(title:www:http://dbpubs.stanford.edu/pub/2000-29)", entered-by = "Sriram Raghavan", keywords = "Text-index Web WebBase", abstract = { We identify crucial design issues in building a distributed inverted index for a large collection of web pages. We introduce a novel pipelining technique for structuring the core index- building system that substantially reduces the index construction time. We also propose a storage scheme for creating and managing inverted files using an embedded database system. We propose and compare different strategies for addressing various issues relevant to distributed index construction. Finally, we present performance results from experiments on a testbed distributed indexing system that we have implemented.} } @INPROCEEDINGS{vander97 ,AUTHOR = "Gregg C. Vanderheiden" ,TITLE = "Anywhere, Anytime (+Anyone) Access to the Next-Generation WWW" ,BOOKTITLE = www97 ,YEAR = "1997" ,entered-by = "Orkut Buyukkokten" ,keywords = "~" ,abstract = {~} } @INPROCEEDINGS{gessler94 ,AUTHOR = "Stean Gessler and Andreas Kotulla" ,TITLE = "PDAs as mobile WWW browsers" ,BOOKTITLE = www94 ,YEAR = "1994" ,entered-by = "Orkut Buyukkokten" ,keywords = "ubiquity, mobile computing, PDA, user interface, wireless, WWW, information service, netservice, bandwidth, client server, multimedia, apple newton, html, http, browser" ,abstract = {~} } @INPROCEEDINGS{domel94 ,AUTHOR = "Peter Domel" ,TITLE = "WebMap: a graphical hypertext navigation tool" ,BOOKTITLE = www94 ,YEAR = "1994" ,entered-by = "Orkut Buyukkokten" ,keywords = "WWW, hypertext visualization, navigation support, Web browser support tool, agent support, event-based object interaction, graphical map, searching, graph layout" ,abstract = {~} } @INPROCEEDINGS{kent94 ,AUTHOR = "Robert E. Kent and Christian Neuss" ,TITLE = "Creating a web analysis and visualization environment" ,BOOKTITLE = www94 ,YEAR = "1994" ,entered-by = "Orkut Buyukkokten" ,keywords = "indexing, resource discovery, concept analysis" ,abstract = {~} } @INPROCEEDINGS{hauck96 ,AUTHOR = "Franz J. Hauck" ,TITLE = "Supporting hierarchical guided tours in the World Wide Web" ,BOOKTITLE = www96 ,YEAR = "1996" ,entered-by = "Orkut Buyukkokten" ,keywords = "guided tours, authoring environments, WWW server" ,abstract = {~} } @INPROCEEDINGS{ngu97 ,AUTHOR = "Daniel Siaw Weng Ngu and Xindong Wu" ,TITLE = "SiteHelper: A Localized Agent that Helps Incremental Exploration of the World Wide Web" ,BOOKTITLE = www97 ,YEAR = "1997" ,entered-by = "Orkut Buyukkokten" ,keywords = "~" ,abstract = {~} } @INPROCEEDINGS{taka97 ,AUTHOR = "Kenji Takahashi and Eugene Liang" ,TITLE = "Analysis and Design of Web-based Information Systems" ,BOOKTITLE = www97 ,YEAR = "1997" ,entered-by = "Orkut Buyukkokten" ,keywords = "~" ,abstract = {~} } @INPROCEEDINGS{pot97 ,AUTHOR = "Michael Potmesil" ,TITLE = "Maps Alive: Viewing Geospatial Information on the WWW" ,BOOKTITLE = www97 ,YEAR = "1997" ,entered-by = "Orkut Buyukkokten" ,keywords = "~" ,abstract = {~} } @INPROCEEDINGS{carr97 ,AUTHOR = "Jeromy Carriere and Rick Kazman" ,TITLE = "WebQuery: Searching and Visualizing the Web through Connectivity" ,BOOKTITLE = www97 ,YEAR = "1997" ,entered-by = "Orkut Buyukkokten" ,keywords = "~" ,abstract = {~} } @INPROCEEDINGS{hui97 ,AUTHOR = "Chia-Hui Chang and Ching-Chi Hsu" ,TITLE = "Customizable Multi-engine Search Tool with Clustering" ,BOOKTITLE = www97 ,YEAR = "1997" ,entered-by = "Orkut Buyukkokten" ,keywords = "~" ,abstract = {~} } @INPROCEEDINGS{maarek97 ,AUTHOR = "Yoelle S. Maarek and Israel Z. Ben Shaul" ,TITLE = "WebCutter: A System for Dynamic and Tailorable Site Mapping" ,BOOKTITLE = www97 ,YEAR = "1997" ,entered-by = "Orkut Buyukkokten" ,keywords = "~" ,abstract = {~} } @INPROCEEDINGS{bach97 ,AUTHOR = "D. Bachiochi and M. Berstene and E. Chouinard and N. Conlan and M. Danchak and T. Furey and C. Neligon and D. Way" ,TITLE = "Usability Studies And Designing Navigational Aids for The World Wide Web" ,BOOKTITLE = www97 ,YEAR = "1997" ,entered-by = "Orkut Buyukkokten" ,keywords = "~" ,abstract = {~} } @INPROCEEDINGS{spertus97 ,AUTHOR = "Ellen Spertus" ,TITLE = "ParaSite: Mining Structural Information on the Web" ,BOOKTITLE = www97 ,YEAR = "1997" ,entered-by = "Orkut Buyukkokten" ,keywords = "~" ,abstract = {~} } @INPROCEEDINGS{kaas00 ,AUTHOR = "Eija Kaasinen and Matti Aaltonen and Juha Kolari and Suvi Melakoski and Timo Laakko" ,TITLE = "Two Approaches to Bringing Internet Services to WAP Devices" ,BOOKTITLE = www00 ,YEAR = "2000" ,entered-by = "Orkut Buyukkokten" ,keywords = "WAP, mobile access, HTML/WML conversion, usability, evaluation" ,abstract = {~} } @INPROCEEDINGS{sarkar92 ,AUTHOR = "Manojit Sarkar and Marc H. Brown" ,TITLE = "Graphical Fisheye Views of Graphs" ,BOOKTITLE = chi92 ,YEAR = "1992" ,entered-by = "Orkut Buyukkokten" ,keywords = "fisheye views, information visualization" ,abstract = {~} } @INPROCEEDINGS{mynatt92 ,AUTHOR = "Barbee T. Mynatt and Laura Marie Leventhal and Keith Instone and John Farhat and Diane S. Rohlman" ,TITLE = "Hypertext or Book: Which is Better for Answering Questions?" ,BOOKTITLE = chi92 ,YEAR = "1992" ,entered-by = "Orkut Buyukkokten" ,keywords = "experimental research, question answering, usability of hypertext, hypertext" ,abstract = {~} } @INPROCEEDINGS{robrt96 ,AUTHOR = "Scott Robertson and Cathleen Wharton and Catherine Ashworth and Marita Franzke" ,TITLE = "Dual Device User Interface Design: PDAs and Interactive Television" ,BOOKTITLE = chi96 ,YEAR = "1996" ,entered-by = "Orkut Buyukkokten" ,keywords = "personal digital assistant(PDA), interactive television(ITV), ubiquitous computing, mobile computing, multiple devices" ,abstract = {~} } @INPROCEEDINGS{card96 ,AUTHOR = "Stuart K. Card and George G. Robertson and William York" ,TITLE = "The WebBook and the Web Forager: An Information Workspace for the World-Wide Web" ,BOOKTITLE = chi96 ,YEAR = "1996" ,entered-by = "Orkut Buyukkokten" ,keywords = "3d graphics, user interfaces, information access, WWW, information workspace, workspace" ,abstract = {~} } @INPROCEEDINGS{barr97 ,AUTHOR = "Rob Barrett and Paul P. Maglio and Daniel C. Kellem" ,TITLE = "How to Personalize the Web" ,BOOKTITLE = chi97 ,YEAR = "1997" ,entered-by = "Orkut Buyukkokten" ,keywords = "agents, WWW, user models" ,abstract = {~} } @INPROCEEDINGS{guchi97 ,AUTHOR = "Tomoharu Yamaguchi and Itaru Hosomi and Toshiaki Miyashita" ,TITLE = "WebStage: An Active Media Enhanced World Wide Web Browser" ,BOOKTITLE = chi97 ,YEAR = "1997" ,entered-by = "Orkut Buyukkokten" ,keywords = "WWW, metaphor, multimedia, information access, passive-user support, media design" ,abstract = {~} } @INPROCEEDINGS{taus97 ,AUTHOR = "Linda Tauscher and Saul Greenberg" ,TITLE = "Revisitation Patterns in World Wide Web Navigation" ,BOOKTITLE = chi97 ,YEAR = "1997" ,entered-by = "Orkut Buyukkokten" ,keywords = "history mechanisms, WWW, web, hypertext, navigation" ,abstract = {~} } @INPROCEEDINGS{golo97 ,AUTHOR = "Gene Golovchinsky" ,TITLE = "Queries? Links? Is there a difference?" ,BOOKTITLE = chi97 ,YEAR = "1997" ,entered-by = "Orkut Buyukkokten" ,keywords = "hypertext, dynamic links, browsing, newspaper metaphor, information exploration, information retrieval" ,abstract = {~} } @INPROCEEDINGS{gentner97 ,AUTHOR = "Don Gentner and Frank Ludolph and Chris Ryan" ,TITLE = "Simplified Applications for Network Computers" ,BOOKTITLE = chi97 ,YEAR = "1997" ,entered-by = "Orkut Buyukkokten" ,keywords = "calendar, email, HotJava views, human interface design, java, minimalist, network computer, NC, simplicity, Web" ,abstract = {~} } @INPROCEEDINGS{LIEB97 ,AUTHOR = "Henry Lieberman" ,TITLE = "Autonomous Interface Agents" ,BOOKTITLE = chi97 ,YEAR = "1997" ,entered-by = "Orkut Buyukkokten" ,keywords = "agents, interface agents, autonomous agents, Web, browsing, search, learning" ,abstract = {~} } @INPROCEEDINGS{pluhn60 ,AUTHOR = "H. P. Luhn" ,TITLE = "Keyword-In-Context Index for Technical Literature (KWIC Index)" ,BOOKTITLE = "American Documentation XI, 4" ,YEAR = "1960" ,pages = {288--295} ,entered-by = "Orkut Buyukkokten" ,keywords = "~" ,abstract = {~} } @INPROCEEDINGS{ishi98 ,AUTHOR = "Kiyokuni Kawachiya and Hiroshi Ishikawa" ,TITLE = "NaviPoint: An Input Device for Mobile Information Browsing" ,BOOKTITLE = chi98 ,YEAR = "1998" ,entered-by = "Orkut Buyukkokten" ,keywords = "input device, information browsing, user interface, PDAs, hand- held devices, mobile computing" ,abstract = {~} } @INPROCEEDINGS{pirolli98 ,AUTHOR = "Peter Pirolli" ,TITLE = "Exploring Browser Design Trade-offs Using a Dynamical Model of Optimal Information Foraging" ,BOOKTITLE = chi98 ,YEAR = "1998" ,entered-by = "Orkut Buyukkokten" ,keywords = "dynamic programming, information foraging, Scatter/Gather, user models" ,abstract = {~} } @INPROCEEDINGS{hchi98 ,AUTHOR = "Ed H. Chi and James Pitkow and Jock Mackinlay and Peter Pirolli and Rich Gossweiler and Stuart K. Card" ,TITLE = "Visualizing the Evolution of Web Ecologies" ,BOOKTITLE = chi98 ,YEAR = "1998" ,entered-by = "Orkut Buyukkokten" ,keywords = "WWW, visualization, log file analysis, temporal analysis, information ecologies, hypertext, documents" ,abstract = {~} } @INPROCEEDINGS{terv98 ,AUTHOR = "Loren Terveen and Will Hill" ,TITLE = "Finding and Visualizing Inter-site Clan Graphs" ,BOOKTITLE = chi98 ,YEAR = "1998" ,entered-by = "Orkut Buyukkokten" ,keywords = "social filtering, collaborative filtering, information access, information retrieval, information visualization, human-computer interaction, computer supported cooperative work, social network analysis, co-citation analysis" ,abstract = {~} } @INPROCEEDINGS{elvins98 ,AUTHOR = "T. Todd Elvins and David R. Nadeau and Rina Schul and David Kirsh" ,TITLE = "Worldlets: 3D Thumbnails for 3D Browsing" ,BOOKTITLE = chi98 ,YEAR = "1998" ,entered-by = "Orkut Buyukkokten" ,keywords = "3d thumbnails, wayfinding, VRML, virtual reality, empirical study" ,abstract = {~} } @INPROCEEDINGS{park00 ,AUTHOR = "Joonah Park and Jinwoo Kim" ,TITLE = "Effects of Contextual Navigation Aids on Browsing Diverse Web Systems" ,BOOKTITLE = chi00 ,YEAR = "2000" ,entered-by = "Orkut Buyukkokten" ,keywords = "context information, navigation, web systems, structure, browsing, hypertext" ,abstract = {~} } @INPROCEEDINGS{arai92 ,AUTHOR = "Kyoichi Arai and Teruo Yokoyama and Yutaka Matsushita" ,TITLE = "A window sytems with leafing through mode: Bookwindow" ,BOOKTITLE = chi92 ,YEAR = "1992" ,entered-by = "Orkut Buyukkokten" ,keywords = "~" ,abstract = {~} } @INPROCEEDINGS{peck92 ,AUTHOR = "Virginia A. Peck and Bonnie E. John" ,TITLE = "Browser-soar: A computational model of a highly interactive task" ,BOOKTITLE = chi92 ,YEAR = "1992" ,entered-by = "Orkut Buyukkokten" ,keywords = "browsing, cognitive models, GOMS, soar" ,abstract = {~} } @INPROCEEDINGS{shaul99 ,AUTHOR = "Israel Ben-Shaul and Michael Herscovici and Michal Jacovi and Yoelle S. Maarek and Dan Pelleg and Menachem Shtalhaim and Vladimir Soroka and Sigalit Ur" ,TITLE = "Adding support for dynamic and focused search with Fetuccino" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Orkut Buyukkokten" ,keywords = "search enhancements, search filtering, search results visualization, site mapping" ,abstract = {~} } @INPROCEEDINGS{syanli99 ,AUTHOR = "Wen-Syan Li and Quoc Vu and Divakant Agrawal and Yoshinori Hara and Hajime Takano" ,TITLE = "PowerBookmarks: a system for personalizable Web information organization, sharing and management" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Orkut Buyukkokten" ,keywords = "WWW, personalization, classification, query, navigation, bookmarks" ,abstract = {~} } @INPROCEEDINGS{gron99 ,AUTHOR = "Kaj Gronbaek and Lennert Sloth and Peter Orbaek" ,TITLE = "Webvise: browser and proxy support for open hypermedia structuring mechanisms on the World Wide Web" ,BOOKTITLE = www99 ,YEAR = "1999" ,entered-by = "Orkut Buyukkokten" ,keywords = "open hypermedia, information structuring, navigation, collaboration, DOM" ,abstract = {~} } @INPROCEEDINGS{jgreen98 ,AUTHOR = "Stephen J. Green" ,TITLE = "Automated link generation: can we do better than term repetition?" ,BOOKTITLE = www98 ,YEAR = "1998" ,entered-by = "Orkut Buyukkokten" ,keywords = "automatic hypertext generation, semantic relatedness" ,abstract = {~} } @INPROCEEDINGS{kopp98 ,AUTHOR = "Eckhart Koppen and Gustaf Neumann" ,TITLE = "A practical approach towards active hyperlinked documents" ,BOOKTITLE = www98 ,YEAR = "1998" ,entered-by = "Orkut Buyukkokten" ,keywords = "XML, DOM, browsers, mobile code, active documents" ,abstract = {~} } @INPROCEEDINGS{cmill98 ,AUTHOR = "Robert C. Miller and Krishna Bharat" ,TITLE = "SPHINX: a framework for creating personal, site-specific Web crawlers" ,BOOKTITLE = www98 ,YEAR = "1998" ,entered-by = "Orkut Buyukkokten" ,keywords = "crawlers, robots, spiders, Web automation, Web searching, Java, end, user programming, mobile code" ,abstract = {~} } @INPROCEEDINGS{chak98 ,AUTHOR = "Soumen Chakrabarti and Byron Dom and Prabhakar Raghavan and Sridhar Rajagopalan and David Gibson and Jon Kleinberg" ,TITLE = "Automatic resource compilation by analyzing hyperlink structure and associated text" ,BOOKTITLE = www98 ,YEAR = "1998" ,entered-by = "Orkut Buyukkokten" ,keywords = "search, taxonomies, link analysis, anchor text, information retrieval" ,abstract = {~} } @INPROCEEDINGS{juhn98 ,AUTHOR = "Jesper Juhne and Anders T. Jensen and Kaj Gronbaek" ,TITLE = "Ariadne: a Java-based guided tour system for the World Wide Web" ,BOOKTITLE = www98 ,YEAR = "1998" ,entered-by = "Orkut Buyukkokten" ,keywords = "guided tours, navigation, hypermedia, presentation" ,abstract = {~} } @INPROCEEDINGS{lhuang98 ,AUTHOR = "Mao Lin Huang and Peter Eades and Robert F. Cohen" ,TITLE = "WebOFDAV - navigating and visualizing the Web on-line with animated context swapping" ,BOOKTITLE = www98 ,YEAR = "1998" ,entered-by = "Orkut Buyukkokten" ,keywords = "WWW, navigation, information visualization, graph drawing" ,abstract = {~} } @INPROCEEDINGS{wbick97 ,AUTHOR = "Timothy W. Bickmore and Bill N. Schilit" ,TITLE = "Digestor: Device-independent Access to the World Wide Web" ,BOOKTITLE = www97 ,YEAR = "1997" ,entered-by = "Orkut Buyukkokten" ,keywords = "~" ,abstract = {~} } @INPROCEEDINGS{eegan89 ,AUTHOR = "Dennis E. Egan and Joel R. Remde and Thomas K. Landauer" ,TITLE = "Behavioral Evaluation and Analysis of a Hypertext Browser" ,BOOKTITLE = chi89 ,YEAR = "1989" ,entered-by = "Orkut Buyukkokten" ,keywords = "hypertext, text retrieaval, learning, documentation, browser" ,abstract = {~} } @INPROCEEDINGS{furnas86 ,AUTHOR = "George W. Furnas" ,TITLE = "Generalized Fisheye Views" ,BOOKTITLE = chi86 ,YEAR = "1986" ,entered-by = "Orkut Buyukkokten" ,keywords = "~" ,abstract = {~} } @INPROCEEDINGS{mchen99 ,AUTHOR = "M. Chen and M. Hearst and J. Hong and J. Lin" ,TITLE = "Cha-Cha: A System for Organizing Intranet Search Results" ,BOOKTITLE = "Proceedings of the second USENIX Symposium on Internet Technologies and SYSTEMS (USITS)" ,YEAR = "1999" ,entered-by = "Orkut Buyukkokten" ,keywords = "~" ,abstract = {~} } @INPROCEEDINGS{chim94 ,AUTHOR = "R. Chimera and K. Wolman and S. Mark and B. Shneiderman" ,TITLE = "An Exploratory Evaluation of Three Interfaces for Browsing Large Hierarchical Tables of Contents" ,BOOKTITLE = "ACM Transactions on Information Systems, 12, 4" ,YEAR = "1994" ,pages = {383--406} ,entered-by = "Orkut Buyukkokten" ,keywords = "~" ,abstract = {~} } @INPROCEEDINGS{feiner88 ,AUTHOR = "S. Feiner" ,TITLE = "Seeing the Forest for the Trees: Hierarchical Display of Hypertext Structure" ,BOOKTITLE = "Conference on Office Information Systems, New York:ACM" ,YEAR = "1988" ,pages = {205--212} ,entered-by = "Orkut Buyukkokten" ,keywords = "~" ,abstract = {~} } @MISC{POSE ,author = "Palm Inc." ,title = "Palm OS Emulator" ,howpublished = "Palm website: http://www.palm.com/dev/tech/tools/emulator/" ,entered-by = "Orkut Buyukkokten" ,keywords = "web clipping, PalmVII" } @INPROCEEDINGS{nation97 ,AUTHOR = "David A. Nation and Catherine Plaisant and Gary Marchionini and Anita Komlodi" ,TITLE = "Visualizing Web Sites using a Hierarchical Table of Contents Browser: WebToc" ,BOOKTITLE = "Proceedings of the third conference on Human Factors and the Web" ,YEAR = "1997" ,entered-by = "Orkut Buyukkokten" ,keywords = "information visualization, exploratory data analysis, graphical representations, hierarchical table of contents, Java applet, WWW, browsing" ,abstract = {~} } @Book{aho83, author = {Alfred Aho and John Hopcroft and Jeffrey Ullman}, title = {Data Structures and Algorithms}, publisher = {Addison-Wesley}, year = {1983}, entered-by = {Sriram Raghavan} } @Misc{Altavista, key = {Altavista}, title = {Altavista Incorporated}, howPublished = {http://www.altavista.com}, links = {title:www:http://www.altavista.com}, entered-by = {Sriram Raghavan} } @Misc{webmap, key = {Webmap}, title = {The Inktomi WebMap}, howPublished = {http://www.inktomi.com/webmap/}, links = {title:www:http://www.inktomi.com/webmap}, entered-by = {Sriram Raghavan} } @Misc{Yahoo, key = {Yahoo}, title = {Yahoo Incorporated}, howPublished = {http://www.yahoo.com}, links = {title:www:http://www.yahoo.com}, entered-by = {Sriram Raghavan} } @Misc{Alexa, key = {Alexa}, title = {Alexa Internet Inc.}, howpublished = {http://www.alexa.com}, links = {title:www:http://www.alexa.com}, entered-by = {Sriram Raghavan} } @MISC{internetArchive ,key = "Internet Archive" ,title = "The Internet Archive" ,howpublished = "http://www.archive.org/" ,entered-by = "Andreas Paepcke" ,links = {title:www:http://www.archive.org/} ,keywords = "archive, alexa" ,abstract = {~} } @Misc{Google, key = {Google}, title = {Google Inc.}, howpublished = {http://www.google.com}, links = {title:www:http://www.google.com}, entered-by = {Sriram Raghavan} } @InProceedings{olson99, author = {M. Olson and K. Bostic and M. Seltzer}, title = {Berkeley {DB}}, booktitle = {Proc. of the 1999 Summer Usenix Technical Conf.}, year = {1999}, month = {June}, entered-by = {Sriram Raghavan} } @InProceedings{brown94a, author = {Eric W. Brown and James P. Callan and W. Bruce Croft and J. Eliot B. Moss}, title = {Supporting Full-Text Information Retrieval with a Persistent Object Store}, booktitle = edbt94, year = {1994}, month = {March}, pages = {365--378}, entered-by = {Sriram Raghavan}, } @InProceedings{brown94b, author = {Eric W. Brown and James P. Callan and W. Bruce Croft}, title = {Fast Incremental Indexing for Full-Text Information Retrieval}, booktitle = vldb94, year = {1994}, month = {September}, pages = {192--202}, entered-by = {Sriram Raghavan}, } @InProceedings{chakr96, author = {S. Chakrabarti and S. Muthukrishnan}, title = {Resource Scheduling for Parallel Database and Scientific Applications}, booktitle = {8th ACM Symposium on Parallel Algorithms and Architectures}, year = {1996}, month = {June}, pages = {329--335}, entered-by = {Sriram Raghavan} } @InProceedings{douglis96, author = {Fred Douglis and Thomas Ball and Yih-Farn Chen and Eleftherios Koutsofios}, title = {WebGUIDE: Querying and Navigating Changes in Web Repositories}, booktitle = www96, year = {1996}, month = {May}, entered-by = {Sriram Raghavan} } @Article{douglis98, author = {Fred Douglis and Thomas Ball and Yih-Farn Chen and Eleftherios Koutsofios}, title = {The AT\&T Internet Difference Engine: Tracking and Viewing Changes on the Web}, journal = {World Wide Web}, year = {1998}, volume = {1}, number = {1}, pages = {27--44}, month = {January}, entered-by = {Sriram Raghavan} } @Article{fal84, author = {C. Faloutsos and S. Christodoulakis}, title = {Signature Files: An Access Method for Documents and its Analytical Performance Evaluation}, journal = tranos, year = {1984}, volume = {2}, number = {4}, pages = {267--288}, month = {October}, entered-by = {Sriram Raghavan} } @Book{gm00, author = {H. Garcia-Molina and J. Ullman and J. Widom}, title = {Database System Implementation}, publisher = {Prentice-Hall}, year = {2000}, entered-by = {Sriram Raghavan} } @InProceedings{gorssman92, author = {D. A. Gorssman and J. R. Driscoll}, title = {Structuring Text within a Relation System}, booktitle = {Proc. of the 3rd Intl. Conf. on Database and Expert System Applications}, year = {1992}, month = {September}, pages = {72--77}, entered-by = {Sriram Raghavan} } @InProceedings{hawking98, author = {D. Hawking and N. Craswell}, title = {Overview of {TREC}-7 Very Large Collection Track}, booktitle = {Proc. of the Seventh Text Retrieval Conf.}, year = {1998}, month = {November}, pages = {91--104}, howPublished = {\url{http://trec.nist.gov/pubs/trec7/papers/vlc\_overview.pdf.gz}}, links = {title:www:http://trec.nist.gov/pubs/trec7/papers/vlc_overview.pdf.gz}, entered-by = {Sriram Raghavan} } @Article{jeong95, author = {B-S. Jeong and E. Omiecinski}, title = {Inverted File Partitioning Schemes in Multiple Disk Systems}, journal = tpds, year = {1995}, volume = {6}, number = {2}, pages = {142--153}, month = {February}, entered-by = {Sriram Raghavan} } @Article{kleinberg99, author = {Jon Kleinberg}, title = {Authoritative Sources in a Hyperlinked Environment}, journal = jacm, year = {1999}, volume = {46}, number = {5}, pages = {604--632}, month = {November}, entered-by = {Sriram Raghavan} } @InProceedings{manber90, author = {Udi Manber and Gene Myers}, title = {Suffix Arrays: A New Method for On-Line String Searches}, booktitle = {Proc. of the 1st ACM-SIAM Symposium on Discrete Algorithms}, year = {1990}, pages = {319--327}, entered-by = {Sriram Raghavan} } @InProceedings{martin86, author = {Patrick Martin and Ian A. Macleod and Brent Nordin}, title = {A Design of a Distributed Full Text Retrieval System}, booktitle = sigir86, year = {1986}, month = {September}, pages = {131--137}, entered-by = {Sriram Raghavan} } @Article{moffat95, author = {A. Moffat and T. Bell}, title = {In situ Generation of Compressed Inverted Files}, journal = jasis, year = {1995}, volume = {46}, number = {7}, pages = {537--550}, entered-by = {Sriram Raghavan} } @Article{moffat96, author = {A. Moffat and J. Zobel}, title = {Self-indexing Inverted Files for Fast Text Retrieval}, journal = tois, year = {1996}, month = {October}, volume = {14}, number = {4}, pages = {349--379}, entered-by = {Sriram Raghavan} } @InProceedings{ngocvo98, author = {Anh NgocVo and Alistair Moffat}, title = {Compressed Inverted Files with Reduced Decoding Overheads}, booktitle = sigir98, year = {1998}, month = {August}, pages = {290--297}, entered-by = {Sriram Raghavan} } @InProceedings{rneto98, author = {B. Ribeiro-Neto and R. Barbosa}, title = {Query Performance for Tightly Coupled Distributed Digital Libraries}, booktitle = dl98, year = {1998}, month = {June}, pages = {182--190}, entered-by = {Sriram Raghavan} } @InProceedings{rneto99, author = {Berthier Ribeiro-Neto and Edleno S. Moura and Marden S. Neubert and Nivio Ziviani}, title = {Efficient Distributed Algorithms to Build Inverted Files}, booktitle = sigir99, year = {1999}, month = {August}, pages = {105--112}, entered-by = {Sriram Raghavan} } @InProceedings{rosen91, author = {Mendel Rosenblum and John K. Ousterhoust}, title = {The Design and Implementation of a Log-structured File System}, booktitle = {Proc. of the 13th Intl. ACM Symposium on Operating Systems Principles}, year = {1991}, month = {October}, pages = {1--15}, entered-by = {Sriram Raghavan} } @TechReport{taher99, author = {Taher Haveliwala}, title = {Efficient Computation of PageRank}, institution = {Database Group, Computer Science Department, Stanford University}, year = {1999}, month = {February}, number = {1999-31}, note = {Available at http://dbpubs.stanford.edu/pub/1999-31}, links = {title:www:http://dbpubs.stanford.edu/pub/1999-31}, entered-by = {Sriram Raghavan} } @InProceedings{tomasic93a, author = {Anthony Tomasic and Hector Garcia-Molina}, title = {Performance of Inverted Indices in Shared-Nothing Distributed Text Document Information Retrieval Systems}, booktitle = pdis93, year = {1993}, month = {January}, pages = {8--17}, entered-by = {Sriram Raghavan} } @Article{tomasic93b, author = {Anthony Tomasic and Hector Garcia-Molina}, title = {Query Processing and Inverted Indices in Shared-Nothing Document Information Retrieval Systems}, journal = vldbj, volume = {2}, number = {3}, year = {1993}, pages = {243--275}, entered-by = {Sriram Raghavan} } @InProceedings{tomasic94, author = {Anthony Tomasic and Hector Garcia-Molina and Kurt Shoens}, title = {Incremental Update of Inverted List for Text Document Retrieval}, booktitle = sigmod94, year = {1994}, month = {May}, pages = {289--300}, entered-by = {Sriram Raghavan} } @InProceedings{viles94, author = {Charles L. Viles}, title = {Maintaining State in a Distributed Information Retrieval System}, booktitle = {32nd Southeast Conf. of the ACM}, year = {1994}, pages = {157--161}, link = {title:www:http://ils.unc.edu/~viles/papers/acm-32sec.ps}, entered-by = {Sriram Raghavan} } @InProceedings{viles95, author = {Charles L. Viles and James C. French}, title = {Dissemination of Collection Wide Information in a Distributed Information Retrieval System}, booktitle = sigir95, year = {1995}, month = {July}, pages = {12--20}, entered-by = {Sriram Raghavan} } @Book{witten99, author = {I. H. Witten and A. Moffat and T. C. Bell}, title = {Managing Gigabytes: Compressing and Indexing Documents and Images}, publisher = {Morgan Kauffman Publishing}, edition = {2nd}, address = {San Francisco}, year = {1999}, entered-by = {Sriram Raghavan} } @InProceedings{zobel92, author = {J. Zobel and A. Moffat and R. Sacks-Davis}, title = {An Efficient Indexing Technique for Full-Text Database Systems}, booktitle = vldb92, year = {1992}, month = {August}, pages = {352--362}, entered-by = {Sriram Raghavan} } @Article{law99, author = {Steve Lawrence and C. Lee Giles}, title = {Accessibility of Information on the Web}, journal = {Nature}, year = {1999}, volume = {400}, pages = {107--109}, entered-by = {Sriram Raghavan} } @Article{law98, author = {Steve Lawrence and C. Lee Giles}, title = {Searching the {World Wide Web}}, journal = {Science}, volume = {280}, number = {5360}, pages = {98}, year = {1998} } @Article{alb99, author = {Reka Albert and Albert-Laszlo Barabasi and Hawoong Jeong}, title = {Diameter of the {World Wide Web}}, journal = {Nature}, year = {1999}, month = {September}, volume = {401}, number = {6749} } @Article{hub99, author = {Bernardo A. Huberman and Lada A. Adamic}, title = {Growth dynamics of the {World-Wide Web}}, journal = {Nature}, year = {1999}, month = {September}, volume = {401}, number = {6749} } @Article{bar99, author = {Albert-Laszlo Barabasi and Reka Albert}, title = {Emergence of Scaling in Random Networks}, journal = {Science}, year = {1999}, month = {October}, volume = {286}, number = {5439}, pages = {509--512} } @INPROCEEDINGS{ziv00, AUTHOR = {Ziv Bar-Yossef and Alexander Berg and Steve Chien and Jittat Fakcharoenphol Dror Weitz}, TITLE = {Approximating Aggregate Queries About Web Pages via Random Walks}, BOOKTITLE = vldb00, YEAR = 2000 } @INPROCEEDINGS{pit97, AUTHOR = {James Pitkow and Peter Pirolli}, TITLE = {Life, Death, and Lawfulness on the Electronic Frontier}, BOOKTITLE = chi97, YEAR = 1997 } @INPROCEEDINGS{doug99, AUTHOR = {Fred Douglis and Anja Feldmann and Balachander Krishnamurthy}, TITLE = {Rate of Change and other metrics: a Live Study of the World Wide Web}, BOOKTITLE = {USENIX Symposium on Internetworking Technologies and Systems}, YEAR = 1999 } @INPROCEEDINGS{brod00, AUTHOR = {Andrei Broder and Ravi Kumar and Farzin Maghoul and Prabhakar Raghavan and Sridhar Rajagopalan and Raymie Stata and Andrew Tomkins and Janet Wiener}, TITLE = {Graph structure in the web: experiments and models}, BOOKTITLE= www00, YEAR = 2000 } @INPROCEEDINGS{dil00, AUTHOR = {M. Diligenti and F. M. Coetzee and S. Lawrence and C. L. Giles and M. Gori}, TITLE = {Focused Crawling Using Context Graphs}, BOOKTITLE = vldb00, YEAR = 2000 } @TECHREPORT{coff97a, AUTHOR = {E.G. Coffman, Jr. and Zhen Liu and Richard R. Weber}, TITLE = "Optimal Robot Scheduling for Web Search Engines", INSTITUTION = "INRIA", YEAR = 1997 } @ARTICLE{koster95, AUTHOR = {Martijn Koster}, TITLE = {Robots in the Web: threat or treat?}, JOURNAL = {ConneXions}, VOLUME = {4}, NUMBER = {4}, MONTH = {April}, YEAR = {1995}, COMMENT = {http://info.webcrawler.com/mak/projects/robots/threat-or- treat.html}, LINK = {http://info.webcrawler.com/mak/projects/robots/threat-or-treat.html} } @MISC{roex, key = {RobotsExclusionProtocol}, TITLE = {Robots Exclusion Protocol}, HOWPUBLISHED = {http://info.webcrawler.com/mak/projects/robots/exclusion.html}, LINK = {http://info.webcrawler.com/mak/projects/robots/exclusion.html} } @InProceedings{bharat98, author = {Krishna Bharat and Andrei Broder and Monika Henzinger and Puneet Kumar and Suresh Venkatasubramanian}, title = {The Connectivity Server: Fast Access to Linkage Information on the Web}, booktitle = www98, year = {1998}, month = {April}, entered-by = {Sriram Raghavan} } @Book{motwani95, author = "Rajeev Motwani and Prabakar Raghavan", title = "Randomized Algorithms", publisher = "Cambridge University Press", year = "1995" } @Techreport{faloutsos95, AUTHOR = "C. Faloutsos and D. Oard", TITLE = "A Survey of Information Retrieval and Filtering Methods", YEAR = "1995", INSTITUTION = "Dept. of Computer Science, University of Maryland" } @INPROCEEDINGS{raghavan97 ,AUTHOR = "Prabhakar Raghavan" ,TITLE = "Information Retrieval Algorithms: A survey" ,BOOKTITLE = "Proceedings of ACM Symposium on Discrete Algorithms" ,YEAR = "1997" } @INPROCEEDINGS{kumar00 ,AUTHOR = "Ravi Kumar and Prabhakar Raghavan and Sridhar Rajagopalan and D. Sivakumar and Andrew Tomkins and Eli Upfal" ,TITLE = "The Web as a graph" ,BOOKTITLE = "Proceedings of the 19th ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems" ,YEAR = "2000" } @INPROCEEDINGS{chakr98 ,AUTHOR = "Soumen Chakrabarti and Byron Dom and Piotr Indyk" ,TITLE = "Enhanced Hypertext Categorization Using Hyperlinks" ,BOOKTITLE = sigmod98 ,YEAR = "1998" } @INPROCEEDINGS{gibson98 ,AUTHOR = "David Gibson and Jon M. Kleinberg and Prabhakar Raghavan" ,TITLE = "Inferring Web Communities from Link Topology" ,BOOKTITLE = "HyperText" ,YEAR = "1998" } @INPROCEEDINGS{fernandez97, author = {Mary F. Fernandez and Daniela Florescu and Jaewoo Kang and Alon Y. Levy and Dan Suciu}, title = {{STRUDEL}: A Web-site Management System}, booktitle = sigmod97, year = {1997}, pages = {549--552}, entered-by = {Sriram Raghavan} } @INPROCEEDINGS{mecca98, author = {Giansalvatore Mecca and Paolo Atzeni and Alessandro Masci and Paolo Merialdo and Giuseppe Sindoni}, title = {The {ARANEUS} Web-Base Management System}, booktitle = sigmod98, year = {1998}, pages = {544--546}, entered-by = {Sriram Raghavan} } @ARTICLE{florescu98, author = {Daniela Florescu and Alon Y. Levy and Alberto O. Mendelzon}, title = {Database Techniques for the World-Wide Web: A Survey}, journal = {SIGMOD Record}, volume = {27}, number = {3}, year = {1998}, pages = {59--74}, entered-by = {Sriram Raghavan} } @BOOK{Golub89 ,AUTHOR = "G. Golub and C. Van Loan" ,TITLE = "Matrix Computations" ,PUBLISHER = "John Hopkins Press" ,YEAR = "1989" } @BOOK{Egghe90 ,AUTHOR = "L. Egghe and R. Rousseau" ,TITLE = "Introduction to Informetrics" ,PUBLISHER = "Elsevier" ,YEAR = "1990" } @ARTICLE{Garfield72 ,AUTHOR = "E. Garfield" ,TITLE = "Citation Analysis as a tool in journal evaluation" ,JOURNAL = "Science" ,VOLUME = "178" ,YEAR = "1972" ,pages = "471-479" } @ARTICLE{Pinski76 ,AUTHOR = "G. Pinski and F. Narin" ,TITLE = "Citation influence for journal aggregates of scientific publications: Theory, with application to the literature of physics" ,JOURNAL = "Inf. Proc. and Management" ,VOLUME = "12" ,YEAR = "1976" } @INPROCEEDINGS{chak98b ,AUTHOR = "Soumen Chakrabarti and Byron Dom and David Gibson and Ravi Kumar and Prabhakar Raghavan and Sridhar Rajagopalan and Andrew Tomkins" ,TITLE = "Spectral Filtering for Resource Discovery" ,BOOKTITLE = "ACM SIGIR workshop on Hypertext Information Retrieval on the Web" ,YEAR = "1998" } @ARTICLE{ange83 ,AUTHOR = "R.C. Angell and G.E. Freund and P. Willett" ,TITLE = "Automatic Spelling Correction Using a Trigram Similarity Measure" ,JOURNAL = "Information Processing and Management" ,YEAR = "1983" ,volume = "19" ,number = "4" ,pages = "255-261" ,entered-by = "Andreas Paepcke" ,keywords = "trigrams, n-grams" ,abstract = {~} } @INPROCEEDINGS{Amento00 ,AUTHOR = "B. Amento and L. Terveen and W. Hill" ,TITLE = "Does authority mean quality? {P}redicting expert quality ratings of web documents." ,BOOKTITLE = sigir00 ,YEAR = "2000" ,publisher = "ACM" ,entered-by = "Arvind Arasu" ,abstract = "evaluating different link based ranking techniques" } @INPROCEEDINGS{lam00 ,AUTHOR = "Wang Lam and Hector Garcia-Molina" ,TITLE = "Multicasting a Web Repository" ,BOOKTITLE = "Submitted for publication" ,YEAR = "2000" ,note = "Available at http://dbpubs.stanford.edu/pub/2000-58" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-58)" ,editor = "~" ,publisher = "~" ,address = "~" ,entered-by = "Andreas Paepcke" ,keywords = "webbase, multicasting, crawling, crawler" ,abstract = {Web crawlers generate signicant loads on Web servers, and are difficult to operate. Instead of running crawlers at many client sites, we propose a central crawler and Web repository that then multicasts appropriate subsets of the central repository to clients. Loads at Web servers are reduced because a single crawler visits the servers, as opposed to all the client crawlers. In this paper we model and evaluate such a central Web multicast facility. We develop multicast algorithms for the facility, comparing them with ones for "broadcast disks." We also evaluate performance as several factors, such as object granularity and client batching, are varied. } } @INPROCEEDINGS{duma88 ,AUTHOR = "Susan T. Dumais and George W. Furnas and Thomas K. Landauer and Scott Deerwester and Richard Harshman" ,TITLE = "Using Latent Semantic Analysis to Improve Access to Textual Information" ,BOOKTITLE = chi88 ,YEAR = "1988" ,entered-by = "Andreas Paepcke" ,keywords = "latent semantic indexing, LSI, information filter" ,abstract = {A main citation for LSI. It explains roughly how it works.} } @ARTICLE{deer90 ,AUTHOR = "Scott Deerwester and Susan T. Dumais and George W. Furnas and Thomas K. Landauer and Richard Harshman" ,TITLE = "Indexing by Latent Semantic Analysis" ,JOURNAL = "Journal of the American Society for Information Science" ,YEAR = "1990" ,month = "June" ,volume = "41" ,entered-by = "Lucy Berlin" ,keywords = "lsi, latent semantic indexing, IR" ,abstract = {~} } @INPROCEEDINGS{folt90 ,AUTHOR = "Peter W. Foltz" ,TITLE = "Using Latent Semantic Indexing for Information Filtering" ,BOOKTITLE = cois90 ,YEAR = "1990" ,entered-by = "Andreas Paepcke" ,found-in = "Paepcke's files" ,keywords = "latent semantic indexing, LSI, news filtering, filters" ,abstract = {LSI study to show how well it predicts interestingness of newsgroup articles.} } @BOOK{hewl98 ,AUTHOR = "Walter B. Hewlett and Eleanor Selfridge-Field, eds." ,TITLE = "Melodic Similarity. Concepts, Procedures, and Applications" ,PUBLISHER = "MIT Press and Center for Computing in the Humanities (CCARH), Stanford University" ,YEAR = "1998" ,entered-by = "Andreas Paepcke" ,keywords = "Collection of papers on searching music for similarity." ,abstract = {} } @BOOK{sank83 ,AUTHOR = "David Sankoff and J.B. Kruskal (ed.)" ,TITLE = "Time Warps, String Edits, and Macromolecules: The Theory and Practice of Sequence Comparison" ,PUBLISHER = "Addison-Wesley" ,YEAR = "1983" ,entered-by = "Andreas Paepcke" ,keywords = "string comparison, sequences, closest editing distance, dynamic programming" ,abstract = {Found this in hewl98 (Smith/McNab/Witten) as a reference for closest editing distance.} } @INCOLLECTION{smit98 ,AUTHOR = "Lloyd A. Smith and Rodger J. McNab and Ian H. Witten" ,TITLE = "Sequence-Based Melodic Comparison: A Dynamic-Programming Approach" ,BOOKTITLE = "Melodic Similarity. Concepts, Procedures, and Applications" ,YEAR = "1998" ,PUBLISHER = "MIT Press and Center for Computing in the Humanities (CCARH), Stanford University" ,editor = "Walter B. Hewlett and Eleanor Selfridge-Field" ,pages = "101-117" ,entered-by = "Andreas Paepcke" ,found-in = "Andreas has a copy" ,keywords = "melodic similarity, music retrieval, dynamic programming, closest editing distance" ,abstract = {Nice summary of dynamic programming and closest editing distance. Shows how to apply the concept to music.} } @INPROCEEDINGS{doorn00 ,AUTHOR = "Mark G.K.M. van Doorn and Arjen P. de Vries" ,TITLE = "The Psychology of Multimedia Databases" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {Multimedia information retrieval in digital libraries is a difficult task for computers in general. Humans on the other hand are experts in perception, concept representation, knowledge organization and memory retrieval. Cognitive psychology and science describe how cognition works in humans, but can offer valuable clues to information retrieval researchers as well. Cognitive psychologists view the human mind as a general-purpose symbol-processing system that interacts with the world. A multimedia information retrieval system can also be regarded as a symbol-processing system that interacts with the environment. Its underlying information retrieval model can be seen as a cognitive framework that describes how the various aspects of cognition are related to each other.} } @INPROCEEDINGS{allen00 ,AUTHOR = "Robert B. Allen and Jane Acheson" ,TITLE = "Browsing the Structure of Multimedia Stories" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {Stories may be analyzed as sequences of causally-related events and reactions to those events by the characters. We employ a notation of plot elements, similar to one developed by Lehnert, and we extend that by forming higher level "story threads". This notation requires that events and reactions be linked and that the chains of links be terminated back to the beginning of the story. Furthermore, we have built a browser for the plot elements, the story threads, and associated multimedia. We apply the browser to Corduroy, a children's short feature which was analyzed in detail. We provide additional illustrations with analysis of Kiss of Death, a Film Noir classic. Effectively, the browser provides a framework for interactive summaries of the narrative.} } @INPROCEEDINGS{wolfe00 ,AUTHOR = "Joanna L. Wolfe" ,TITLE = "Effects of Annotations on Student Readers and Writers" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {Recent research on annotations has focused on how readers annotate texts, ignoring the question of how reading annotations might affect subsequent readers of a text. This paper reports on a study of persuasive essays written by 123 undergraduates receiving primary source materials annotated in various ways. Findings indicate that annotations improve recall of emphasized items, influence how specific arguments in the source materials are perceived, decrease students' tendencies to unnecessarily summarize. Of particular interest is that students' perceptions of the annotator appeared to greatly influence how they responded to the annotated material. Using this study as a basis, I discuss implications for the design and implementation of digitally annotated materials.} } @INPROCEEDINGS{brown00 ,AUTHOR = "Michael S. Brown and W. Brent Seales" ,TITLE = "Beyond 2D Images: Effective 3D Imaging for Library Materials" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {Significant efforts are being made to digitize rare and valuable library materials, with the goal of providing patrons and historians digital facsimiles that capture the look and feel of the original materials. This is often done by digitally photographing the materials and making high resolution 2D images available. The underlying assumption is that the objects are flat. However, older materials may not be flat in practice, being warped and crinkled due to decay, neglect, accident and the passing of time. In such cases, 2D imaging is insufficient to capture the look and feel of the original. For these materials, 3D acquisition is necessary to create a realistic facsimile. This paper outlines a technique for capturing an accurate 3D representation of library materials which can be integrated directly into current digitization setups. This will allow digitization efforts to provide patrons with more realistic digital facsimile of library materials.} } @INPROCEEDINGS{cras00 ,AUTHOR = "Nick Craswell and Peter Bailey" ,TITLE = "Server Selection on the World Wide Web" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {We evaluate server selection methods in a Web environment, modeling a digital library which makes use of existing Web search servers rather than building its own index. The evaluation framework portrays the Web realistically in several ways. Its search servers index real Web documents, are of various sizes, cover different topic areas and employ different retrieval methods. Selection is based on statistics extracted from the results of probe queries submitted to each server. We evaluate published selection methods and a new method for enhancing selection based on expected search server effectiveness. Results show CORI to be the most effective of three published selection methods.} } @INPROCEEDINGS{feke00 ,AUTHOR = "Jean-Daniel Fekete and Micole Dufournaud" ,TITLE = "Compus: Visualization and Analysis of Structured Documents for Understanding Social Life in the 16th Century" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {This article describes the Compus visualization system that assists in the exploration and analysis of structured document copora encoded in XML. Compus has been developed for and applied to a corpus of 100 French manuscript letters of the 16th century, transcribed and encoded for scholarly analysis using the recommendations of the Text Encoding Initiative. By providing a synoptic visualization of a corpus and allowing for dynamic queries and structural transformations, Compus assists researchers in finding regularities or discrepancies, leading to a higher level analysis of historic source. compus can be used with other richly encoded text copora as well.} } @INPROCEEDINGS{Shneid00 ,AUTHOR = "Ben Shneiderman and David Felsman and Anne Rose and Xavier Ferre Grau" ,TITLE = "Visualizing Digital Library Search Results with Categorical and Hierarchical Axes" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {Digital library search results are usually shown as a textual list, with 10-20 items per page. Viewing several thousand search results at once on a two-dimensional display with continuous variables is a promising alternative. Since these displays can overwhelm some users, we created a simplified two-dimensional display that uses categorical and hierarchical axes, called hieraxes. Users appreciate the meaningful and limited number of terms on each hieraxis. At each grid point of the display we show a cluster of color-coded dots or a bar chart. Users see the entire result set and can then click on labels to move down a level in the hierarchy. Handling broad hierarchies and arranging for imposed hierarchies led to additional design innovations. We applied hieraxes to a digital video library of science topics used by middle school teachers, a legal information system, and a technical library using the ACM Computing Classification System. Feedback from usability testing with 32 subjects revealed strengths and weaknesses.} } @INPROCEEDINGS{moh00 ,AUTHOR = "Chuang-Huc Moh and Ee-Peng Lim and Wee-Keong Ng" ,TITLE = "Re-engineering Structures from Web Documents" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {To realise a wide range of applications (including digital libraries) on the Web, a more structured way of accessing the Web is required and such requirement can be facilitated by the use of XML standard. In this paper, we propose a general framework for reverse engineering (or re-engineering) the underlying structures i.e., the DTD from a collection of similarly structured XML documents when they share some common but unknown DTDs. The essential data structures and experiments on real Web collections have been conducted to demonstrate their feasibility. In addition, we also proposed a method of imposing a constraint on the repetitiveness on the elements in a DTD rule to further simplify the generated DTD without compromising their correctness. } } @INPROCEEDINGS{giuff00 ,AUTHOR = "Giovanni Giuffrida and Eddie C. Shek and Jihoon Yang" ,TITLE = "Knowledge-Based Metadata Extraction from PostScript Files" ,BOOKTITLE = dl00 ,entered-by = "Rebecca Wesley" ,abstract = {The automatic document metadata extraction process is an important task in a world where thousands of documents are just one click away. Thus, powerful indices are necessary to support effective retrieval. The upcoming XML standard represents an important step in this direction as its semistructured representation conveys document metadata together with the text of the document. For example, retrieval of scientific papers by authors or affiliations would be a straightforward task if papers were stored in XML. Unfortunately, today, the largest majority of documents on the web are available in forms that do not carry additional semantics. Converting existing documents to a semistructured representation is time consuming and no automatic process can be easily applied. In this paper we discuss a system, based on a novel spatial/visual knowledge principle, for extracting metadata from scientific papers stored as PostScript files. Our system embeds the general knowledge about the graphic layout of a scientific paper to guide the metadata extraction process. Our system can effectively assist the automatic index creation for digital libraries.} } @INPROCEEDINGS{agic00 ,AUTHOR = "Eugene Agichtein and Luis Gravano" ,TITLE = "Snowball: Extracting Relations from Large Plain-Text Collections" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {Text documents often contain valuable structured data that is hidden in regular English sentences. This data is best exploited if available as a relational table that we could use for answering precise queries or for running data mining tasks. We explore a technique for extracting such tables from document collections that requires only a handful of training examples from users. these examples are used to generate extraction patterns, that in turn result in new tuples being extracted from the document collection. We build on this idea and present our Snowball system. Snowball introduces novel strategies for generating patterns and extracting tuples from plain-text documents. At each iteration of the extraction process, Snowball evaluates the quality of these patterns and tuples without human intervention, and keeps only the most reliable ones for the next iteration. In this paper we also develop a scalable evaluation methodology and metrics for our task, and present a thorough experimental evaluation of Snowball and comparable techniques over a collection for more than 300,000 newspaper documents.} } @INPROCEEDINGS{jones00 ,AUTHOR = "Michael L.W. Jones and Robert H. Rieger and Paul Treadwell and Geri K. Gay" ,TITLE = "Live from the Stacks: User Feedback on Mobile Computers and Wireless Tools for Library Patrons" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {Digital library research is made more robust and effective when end-user opinions and viewpoints inform the research, design and development process. A rich understanding of user tasks and contexts is especially necessary when investigation the use of mobile computers in traditional and digital library environments, since the nature and scope of the research questions at hand remain relatively undefined. This paper outlines findings from a library technologies user survey and on-site mobile library access prototype testing, and presents future research directions that can be derived from the results of these two studies.} } @INPROCEEDINGS{neves00 ,AUTHOR = "Fernando A. Das Neves and Edward A. Fox" ,TITLE = "A Study of User Behavior in an Immersive Virtual Environment for Digital Libraries" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {In this paper we present a 2x3 factorial design study evaluating the limits and differences on the behavior of 10 users when searching in a virtual reality representation that mimics the arrangement of a traditional library. The focus of this study was the effect of clustering techniques and query highlighting on search strategy users develop in the virtual environment, and whether position or spatial arrangement influenced user behavior. We found several particularities that can be attributed to the differences in the VR environment. This study's results identify: 1) the need of co-designing both spatial arrangement and interaction method; 2) a difficulty novice users faced when using clusters to identify common topics; 3) the influence of position and distance on users' selection of collection items to inspect; and 4) that users did not search until they found the best match, but only until they found a satisfactory match.} } @INPROCEEDINGS{witten00 ,AUTHOR = "Ian H. Witten and Rodger J. McNab and Stefan J. Boddie and David Bainbridge" ,TITLE = "Greenstone: A Comprehensive Open-Source Digital Library Software System" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {This paper describes the Greenstone digital library software, a comprehensive, open_source system for the construction and presentation of information collections. Collections built with Greenstone offer effective full-text searching and metadata-based browsing facilities that are attractive and easy to use. Moreover, they are easily maintainable and can be augmented and rebuilt entirely automatically. The system is extensible: software plugins accommodate different document and metadata types} } @INPROCEEDINGS{yao00 ,AUTHOR = "Ke-Thia Yao and In-Young Ko and Ragy Eleish and Robert Neches" ,TITLE = "Asynchronous Information Space Analysis Architecture Using Content and Structure-Based Service Brokering" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {Our project focuses on rapid formation and utilization of custom collections of information for groups focused on high-paced tasks. Assembling such collections, as well as organizing and analyzing the documents within them, is a complex and sophisticated task. It requires understanding what information management services and tools are provided by the system, when they are appropriate to use, and how those services can be composed together to perform more complex analyses. This paper describes the architecture of a prototype implementation for the information analysis management system that we have developed. The architecture uses metadata to describe collections of documents both in terms of their content and structure. This metadata allows the system to dynamically and in a context-sensitive manner to determine the set of appropriate analysis services. To facilitate the invocation of those services, the architecture also provides and asynchronous and transparent service access mechanism.} } @INPROCEEDINGS{hitch00 ,AUTHOR = "Steve Hitchcock and Les Carr and Zhuoan Jiao and Donna Bergmark and Wendy Hall and Carl Lagoze and Stevan Harnad" ,TITLE = "Developing Services for Open Eprint Archives: Globalisation, Integration and the Impact of Links" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {The rapid growth of scholarly information resources available in electronic form and their organisation by digital libraries is proving fertile ground for the development of sophisticated new services, of which citation linking with be one indispensable example. Many new projects, partnerships and commercial agreements have been announced to build citation linking applications. This paper describes the Open Citation (OpCit) project, which will focus on linking papers held in freely accessible eprint archives such as the Los Alamos physics archives and other distributed archives, and which will build on the work of the Open Archives initiative to make the data held in such archives available to compliant services. The paper emphasises the work of the project in the context of emerging digital library information environments, explores how a range of new linking tools might be combined and identifies ways in which different linking applications might converge. Some early results of linked pages from OpCit project are reported.} } @INPROCEEDINGS{goh00 ,AUTHOR = "Dion Goh and John Leggett" ,TITLE = "Patron-augmented Digital Libraries" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {Digital library research is mostly focused on the generation of large collections of multimedia resources and state-of-the-art tools for their indexing and retrieval. However, digital libraries should provide more than advanced collection maintenance and retrieval services since the ultimate goal of any academic library is to serve the scholarly needs of its users. This paper begins by presenting a case for digital scholarship in which patrons perform all scholarly work electronically. A proposal is then made for patron-augmented digital libraries (PADLs), a class of digital libraries that supports the digital scholarship of its patrons. Finally, a prototype PADL (called Synchrony) providing access to video segments and associated textual transcripts is described. Synchrony allows patrons to search the library for artifacts, create annotations/original compositions, integrate these artifacts to form synchronized mixed text and video presentations and, after suitable review, publish these presentations into the digital library if desired. A study to evaluate the PADL concept and usability of Synchrony is also discussed. The study revealed that participants were able to use Synchrony for the authoring and publishing of presentations and that attitudes toward PADLs were generally positive.} } @INPROCEEDINGS{smith00 ,AUTHOR = "Lloyd A. Smith and Elaine F. Chiu and Brian L. Scott" ,TITLE = "A Speech Interface for Building Musical Score Collection" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {Building machine readable collections of musical scores is a tedious and time consuming task. The most common interface for performing music data entry is a mouse and toolbar system; using the mouse, the user selects a rhythm (note shape) from a toolbar, then drags the note to the correct position on the staff. We compare the usability of a hybrid speech and mouse-driven interface to a traditional mouse-driven one. The speech-enhanced interface allows users to enter note rhythms by voice, while still using the mouse to indicate pitches. While task completion time is nearly the same, users (N=13) significantly preferred the speech-augmented interface. A second study using the first two authors of this paper (N=2) indicates that experienced users can enter music 11% faster with the speech interface. Many users expressed a desire to enter pitches, as well as rhythms, by speech. A third study, however, shows that the recognizer is unable to reliably distinguish among A, B, C, D, E, F and G (N=10).} } @INPROCEEDINGS{waugh00 ,AUTHOR = "Andrew Waugh and Ross Wilkinson and Brendan Hills and Jon Dell'oro" ,TITLE = "Preserving Digital Information Forever" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {Well within our lifetime we can expect to see most information being created, stored and used digitally. Despite the growing importance of digital data, the wider community pays almost no attention to the problems of preserving this digital information for the future. Even within the archival and library communities most work on digital preservation has been theoretical, not practical, and highlights the problems rather than giving solutions. Physical libraries have to preserve information for long periods and this is no less true of their digital equivalents. This paper describes the preservation approach adopted in the Victorian Electronic Record Strategy (VERS) which is currently being trailed within the Victorian government, one of the state of Australia. We review the various preservation approaches that have been suggested and describe in detail encapsulation, the approach which underlies the Vers format. A key difference between the VERS project and previous digital preservation projects is the focus within VERS on the construction of actual system to test and implement the proposed technology. VERS is not a theoretical study in preservation.} } @INPROCEEDINGS{snym00 ,AUTHOR = "MMM Snyman and M Jansen van Rensburg" ,TITLE = "Revolutionizing Name Authority Control" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {A new model has been developed for the standardization of names in bibliographic databases. This paper describes the model and its implementation and also compares it with an existing model. The results show that the new model will revolutionize name authority control and will also improve on the existing NACO model. A prototype that was developed also indicates the technical feasibility of the model's implementation.} } @INPROCEEDINGS{moon00 ,AUTHOR = "Raymond J. Mooney" ,TITLE = "Content-Based Book Recommending Using Learning for Text Categorization" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {Recommender systems improve access to relevant products and information by making personalized suggestions based on previous examples of a user's likes and dislikes. Most existing recommender systems use collaborative filtering methods that base recommendations on other users' preferences. By contrast, content-based methods use information about an item itself to make suggestions. This approach has the advantage of being able to recommend previously unrated items to users with unique interests and to provide explanations for its recommendations. We describe a content-based book recommending system that utilizes information extraction and a machine-learning algorithm for text categorization. Initial experimental results demonstrate that this approach can produce accurate recommendations.} } @INPROCEEDINGS{lark00 ,AUTHOR = "Leah S. Larkey and Paul Ogilvie and M. Andrew Price and Brenden Tamilio" ,TITLE = "Acrophile: An automated Acronym Extractor and Server" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {We implemented a web server for acronym and abbreviation lookup, containing a collection of acronyms and their expansions gathered from a large number of web pages by a heuristic extraction process. Several different extraction algorithms were evaluated and compared. The corpus resulting from the best algorithm is comparable to a high-quality hand-crafted site, but has the potential to be much more inclusive as data from more web pages are processed.} } @INPROCEEDINGS{payn00 ,AUTHOR = "Gordon W. Paynter and Ian H. Witten and Sally Jo Cunningham and George Buchanan" ,TITLE = "Scalable Browsing for Large Collections: A Case Study" ,BOOKTITLE = dl00 ,YEAR = "2000" ,entered-by = "Rebecca Wesley" ,abstract = {Phrase browsing techniques use phrases extracted automatically from a large information collection as a basis for browsing and accessing it. This paper describes a case study that uses an automatically constructed phrase hierarchy to facilitate browsing of an ordinary large Web site. Phrases are extracted from the full text using a novel combination of rudimentary syntactic processing and sequential grammar induction techniques. The interface is simple, robust and easy to use.} } @INPROCEEDINGS{meln00a ,AUTHOR = "Sergey Melnik" ,TITLE = "Declarative Mediation in Distributed Systems" ,BOOKTITLE = "Proceedings of the International Conference on Conceptual Modeling (ER'00)" ,YEAR = "2000" ,month = "October" ,address = "Salt Lake City" ,entered-by = "Andreas Paepcke" ,keywords = "interoperability, service mediation" ,abstract = {~} } @MISC{corba01 ,title = "CORBA Website" ,howpublished = "http://www.corba.org" ,links = "(title:www:http://www.corba.org)" ,entered-by = "Andreas Paepcke" ,keywords = "CORBA" ,abstract = {~} } @Misc{amazon, key = {Amazon}, title = {Amazon Inc.}, howpublished = {http://www.amazon.com}, links = {title:www:http://www.amazon.com}, entered-by = {Sriram Raghavan} } @Misc{asp, key = {ASP}, title = {{A}ctive {S}erver {P}ages Technology}, howPublished = {http://msdn.microsoft.com/workshop/server/asp/aspfeat.asp}, links = {title:www:http://msdn.microsoft.com/workshop/server/asp/aspfeat.asp}, entered-by = {Sriram Raghavan} } @Misc{bpwhitepaper, key = {BrightPlanet White Paper}, title = {The {D}eep {W}eb: {S}urfacing {H}idden {V}alue}, howPublished = {http://www.completeplanet.com/Tutorials/DeepWeb/}, links = {title:www:http://www.completeplanet.com/Tutorials/DeepWeb/}, entered-by = {Sriram Raghavan} } @Misc{brightplanet, key = {BrightPlanet}, title = {BrightPlanet.com}, howPublished = {http://www.brightplanet.com}, links = {title:www:http://www.brightplanet.com}, entered-by = {Sriram Raghavan} } @Misc{cgi, key = {cgi}, title = {{C}ommon {G}ateway {I}nterface ({CGI})}, howPublished = {http://hoohoo.ncsa.uiuc.edu/cgi/overview.html}, links = {title:www:http://hoohoo.ncsa.uiuc.edu/cgi/overview.html}, entered-by = {Sriram Raghavan} } @Misc{dom, key = {dom}, title = {{D}ocument {O}bject {M}odel {L}evel 1 Specification}, howPublished = {http://www.w3.org/TR/REC-DOM-Level-1/}, links = {title:www:http://www.w3.org/TR/REC-DOM-Level-1/}, entered-by = {Sriram Raghavan} } @Book{dp80, author = {D. Dubois and H. Prade}, title = {Fuzzy Sets and Systems: Theory and Applications}, publisher = {Academic Press, New York}, year = {1980}, entered-by = {Sriram Raghavan} } @Article{presti97, author = {Daniel Lopresti and Andrew Tomkins}, title = {Block Edit Models for Approximate String Matching}, journal = {Theoretical Computer Science}, year = {1997}, volume = {181}, number = {1}, pages = {159--179}, month = {July}, entered-by = {Sriram Raghavan} } @Book{zimm96, author = {H.-J.Zimmermann}, title = {Fuzzy Set Theory}, publisher = {Kluwer Academic Publishers}, year = {1996}, entered-by = {Sriram Raghavan} } @Article{heydon99, author = {Allan Heydon and Marc Najork}, title = {Mercator: A Scalable, Extensible {W}eb Crawler}, journal = {World Wide Web}, year = {1999}, volume = {2}, number = {4}, pages = {219--229}, month = {December}, entered-by = {Sriram Raghavan} } @Misc{htmlforms, key = {htmlforms}, title = {Forms in {HTML} Documents -- {W3C} {HTML} 4.01 Recommendation}, howPublished = {http://www.w3.org/TR/html401/interact/forms.html}, links = {title:www:http://www.w3.org/TR/html401/interact/forms.html}, entered-by = {Sriram Raghavan} } @Misc{httpspec, key = {httpspec}, title = {Hypertext Transfer Protocol -- {HTTP/1.1}}, howPublished = {ftp://ftp.isi.edu/in-notes/rfc2616.txt}, links = {title:www:ftp://ftp.isi.edu/in-notes/rfc2616.txt}, entered-by = {Sriram Raghavan} } @Misc{invisibleweb, key = {Invisible Web}, title = {InvisibleWeb.com}, howPublished = {http://www.invisibleweb.com}, links = {title:www:http://www.invisibleweb.com}, entered-by = {Sriram Raghavan} } @Misc{jsp, key = {jsp}, title = {JavaServer Pages (JSP\texttrademark) Technology}, howPublished = {http://java.sun.com/products/jsp/}, links = {title:www:http://java.sun.com/products/jsp/}, entered-by = {Sriram Raghavan} } @Misc{opendir, key = {opendir}, title = {Open Directory}, howPublished = {http://www.dmoz.org}, links = {title:www:http://www.dmoz.org}, entered-by = {Sriram Raghavan} } @Misc{php, key = {php}, title = {{PHP} {H}ypertext {P}rocessor}, howPublished = {http://www.php.net}, links = {title:www:http://www.php.net}, entered-by = {Sriram Raghavan} } @Misc{servlet, key = {servlet}, title = {Java Servlet\texttrademark Technology}, howPublished = {http://java.sun.com/products/servlet/}, links = {title:www:http://java.sun.com/products/servlet/}, entered-by = {Sriram Raghavan} } @TechReport{ragh00, author = {Sriram Raghavan and Hector Garcia-Molina}, title = {Crawling the Hidden Web}, institution = {Computer Science Department, Stanford University}, year = {2000}, month = {December}, number = {2000-36}, note = {Available at http://dbpubs.stanford.edu/pub/2000-36}, links = {title:www:http://dbpubs.stanford.edu/pub/2000-36}, entered-by = {Sriram Raghavan} } @InProceedings{gupta98, author = {A. Gupta and V. Harinarayan and A. Rajaraman}, title = {Virtual Database Technology}, booktitle = icde98, year = {1998}, month = {February}, pages = {23--27}, entered-by = {Sriram Raghavan} } @Misc{whizbanglabs, key = {whizbanglabs}, title = {Whizbang! Labs}, howPublished = {http://www.whizbanglabs.com}, links = {title:www:http://www.whizbanglabs.com}, entered-by = {Sriram Raghavan} } @InProceedings{diligenti00, author = {Michelangelo Diligenti and Frans Coetzee and Steve Lawrence and C. Lee Giles and Marco Gori}, title = {Focused Crawling Using Context Graphs}, booktitle = vldb00, year = {2000}, month = {September}, pages = {527--534}, entered-by = {Sriram Raghavan} } @INPROCEEDINGS{buyu01 ,AUTHOR = "Orkut Buyukkokten and Hector Garcia-Molina and Andreas Paepcke" ,TITLE = "Seeing the Whole in Parts: Text Summarization for Web Browsing on Handheld Devices" ,BOOKTITLE = www01 ,YEAR = "2001" ,note = "Available at http://dbpubs.stanford.edu/pub/2001-45" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2001-45)" ,entered-by = "Andreas Paepcke" ,keywords = "power browser, summarization" ,abstract = {We introduce five methods for summarizing parts of Web pages on handheld devices, such as personal digital assistants (PDAs), or cellular phones. Each Web page is broken into text units that can each be hidden, partially displayed, made fully visible, or summarized. The methods accomplish summarization by different means. One method extracts significant keywords from the text units, another attempts to find each text unit's most significant sentence to act as a summary for the unit. We use information retrieval techniques, which we adapt to the World-Wide Web context. We tested the relative performance of our five methods by asking human subjects to accomplish single-page information search tasks using each method. We found that the combination of keywords and single-sentence summaries works best for a variety of search tasks.} } @INPROCEEDINGS{kalj01 ,AUTHOR = "Oliver Kaljuvee and Orkut Buyukkokten and Hector Garcia-Molina and Andreas Paepcke" ,TITLE = "Efficient Web Form Entry on PDAs" ,BOOKTITLE = www01 ,YEAR = "2001" ,note = "Available at http://dbpubs.stanford.edu/pub/2001-44" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2001-44)" ,entered-by = "Andreas Paepcke" ,keywords = "Power Browser" ,abstract = {We propose a design for displaying and manipulating HTML forms on small PDA screens. The form input widgets are not shown until the user is ready to fill them in. At that point, only one widget is shown at a time. The form is summarized on the screen by displaying just the text labels that prompt the user for each widget's information. The challenge of this design is to automatically find the match between each text label in a form, and the input widget for which it is the prompt. We developed eight algorithms for performing such label/widget matches. Some of the algorithms are based on n-gram comparisons, while others are based on common form layout conventions. We applied a combination of these algorithms to 100 simple HTML forms with an average of four input fields per form. These experiments achieved a 95% matching accuracy. We developed a scheme that combines all algorithms into a matching system. This system did well even on complex forms, achieving 80% accuracy in our experiments involving 330 input fields spread over 48 complex forms. } } @ARTICLE{aras01 ,AUTHOR = "Arvind Arasu and Junghoo Cho and Hector Garcia-Molina and Andreas Paepcke and Sriram Raghavan" ,TITLE = "Searching the Web" ,JOURNAL = toit ,YEAR = "2001" ,note = "Submitted for publication. Available at http://dbpubs.stanford.edu/pub/2000-37" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-37)" ,entered-by = "Andreas Paepcke" ,keywords = "searching, crawling, webbase" ,abstract = {We offer an overview of current Web search engine design. After introducing a generic search engine architecture, we examine each engine component in turn. We cover crawling, local Web page storage, indexing, and the use of link analysis for boosting search performance. The most common design and implementation techniques for each of these components are presented. We draw for this presentation from the literature, and from our own experimental search engine testbed. Emphasis is on introducing the fundamental concepts, and the results of several performance analyses we conducted to compare different designs. } } @InProceedings{ragh01, author = {Sriram Raghavan and Hector Garcia-Molina}, title = {Crawling the Hidden Web}, booktitle = vldb01, year = {2001}, month = {September}, entered-by = {Sriram Raghavan} } @InProceedings{mccallum99, author = {A. McCallum and K. Nigam and J. Rennie and K. Seymore}, title = {Building domain-specific search engines with machine learning techniques}, booktitle = {Proceedings of the AAAI Spring Symposium on Intelligent Agents in Cyberspace}, year = {1999}, entered-by = {Sriram Raghavan} } @INPROCEEDINGS{rauber01 ,AUTHOR = "Andreas Rauber and Alexander Muller-Kogler" ,TITLE = "Integrating Automatic Genre Analysis into Digital Libraries" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {With the number and types of documents in digital library systems increasing, tools for automatically organizaing and presenting the content have to be found. While many approaches focus on topic-based organization and structuring, hardly any system incorporates automatic structural analysis and representation. Yet, genre information (unconsciously) forms one of the most distinguishing features in conventional libraries and in information searches. In this paper we present an approach to automatically analyze the structure of documents and to integrate this information into an automatically created content-based organization. In the resulting visualization, documents on similar topics, yet representing different genres, are depicted as books in differing colors. This representation supports users intuitively in locating relevant information presented in a relvant form.} } @INPROCEEDINGS{frasconi01 ,AUTHOR = "Paolo Frasconi and Giovanni Soda and Alessandro Vullo" ,TITLE = "Text Categorization for Multi-page Documents: A Hybrid Naive Bayes HMM Approach" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {Text categorization is typically formulated as a concept learning problem where each instance is a single isolated document. In this paper we are interested in a moe general formulation where documents are organized as page sequences, as naturally occurring in digital libraries of scanned books and magazines. We describe a method for classifying pages of sequential OCR text dosuments into one of several assigned categories and suggest that taking into account contextual information provided by the whole page sequence can significantly improve classification accuracy. The proposed architecture relies on hidden Markov models whose emissions are bag-of-words according to a multinomial word event model, as in the generative portion of the Naive Bayes classifier. Our results on a collection of scanned journals from the Making of America project contirm the importance of using whole page sequences. Empirical evaluation indicates that the error rate (as obtained by running a plain Naive Bayes classifier on isolated page) can be roughly reduced by hald if contextual information is incorporated.} } @INPROCEEDINGS{Yaron01 ,AUTHOR = "David Yaron and D. Jeff Milton and Rebecca Freeland" ,TITLE = "Linked Active Content: A Service for Digital Libraries for Education" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {A service is described to help enable digital libraries for education, such as the NSDL, to serve as collaboration spaces for the creation, modification and use of active learning experiences. The goal is to redefine the line between those activities that fall within the domain of computer programming and those that fall within the domain of content authoring. The current location of this line, as defined by web technologies, is such that far too much of the design and development process is in the domain of software creation. This paper explores the definition and use of "linked active content", which builds on the hypertext paradigm by extending it to support active content. This concept has community development advantages, since it provides an authoring paradigm that supports contributions from a more diverse audience, including especially those who have substantial classroom and pedagogical expertise but lack programming expertise. It also promotes the extraction of content from software so that collections may be better organized and more easily repurposed to meet the needs of a diverse audience of educations and students.} } @INPROCEEDINGS{Laleuf01 ,AUTHOR = "Jean R. Laleuf and Anne Morgan Spalter" ,TITLE = "A Component Repository for Learning Objects: A Progress Report" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {We believe that an important category of SMET digital library content will be highly interactive, explorable microworlds for teaching science, mathematics, and engineering concepts. Such environments have proved extraordinarily time-consuming and difficult to produce, however, threatening the goals of widespread creation and use. One proposed solution for accelerating production has been the creation of repositories of reusable software components or learning objects. Programmers would use such components to rapidly assemble larger-scale environments. Although many agree on the value of this approach, few repositories of such components have been successully created. We suggest some reasons for the lack of expected results and propose two strategies for developing such repositories. We report on a case study that provides a proof of concept of these strategies.} } @INPROCEEDINGS{Marshall01 ,AUTHOR = "Catherine C. Marshall and Morgan N. Price and Gene Golovchinsky and Bill N. Schilit" ,TITLE = "Designing e-Books for Legal Research" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {In this paper we report the findings from a field study of legal research in a first-tier law school and on the resulting redesign of XLibris, a next-generation e-book. We first characterize a work setting in which we expected an e-book to be a useful interface for reading and otherwise using a mix of physical and digital library materials, and explore what kinds of reading-related functionality would bring value to this setting. We do this by describing important aspects of legal research in a heterogeneous information environment, including mobility, reading, annotation, link following and writing practices, and their general implications for design. We then discuss how our work with a user community and an evolving e-book prototype allowed us to examine tandem issues of usability and utility, and to redesign an existing e-book user interface to suit the needs of law students. The study caused us to move away from the notion of a stand-alone reading device and toward the concept of a document laptop, a platform that would provide wireless access to information resources, as well as support a fuller spectrum of reading-related activities.} } @INPROCEEDINGS{Lagoze01 ,AUTHOR = "Carl Lagoze and Herbert Van de Sompel" ,TITLE = "The Open Archives Initiative: Building a Low-Barrier Interoperability Framework" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {The Open Archive Initiative (OAI) develops and promotes interoperability solutions that aim to facilitate the efficient dissemination of content. The roots of the OAI lie in the E-Print community. Over the last year its focus has been extended to include all content providers. This paper describes the recent history of the OAI - its origins in promoting E-Prints, the broadening of its focus, the details of its technical standard for metadata harvesting, the applications of this standard, and future plans} } @INPROCEEDINGS{Revilla01 ,AUTHOR = "Luis Francisco-Revilla and Frank Shipman and Richard Furuta and Unmil Karadkar and Avital Arora" ,TITLE = "Managing Change on the Web" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {Increasingly, digital libraries are being defined that collect pointers to World-Wide Web based resources rather than hold the resources themselves. Maintaining these collections is challenging due to distributed document owership and high fluidity. Typically a collection's maintainer has to assess the relevance of changes with little system aid. In this paper, we describe the Walden's Paths Path Manager, which assists a maintainer in discovering when relevant changes occur to linked resources. The approach and system design was informed by a study of how humans perceive changes of Web pages. The study indicated that structural changes are key in determining the overall change and that presentation changes are considered irrelevant.} } @INPROCEEDINGS{Chau01 ,AUTHOR = "Michael Chau" ,TITLE = "Personalized Spiders for Web Search and Analysis" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {Searching for useful information on the World Wide Web has become increasingly difficult. While Internet search engines have been helping people to search on the web, low recall rate and outdated indexes have become more and more problematic as the web grows. In addition, search tools usually present to the user only a list of search results, failing to provide further personalized analysis which could help users identify useful information and comprehend these results. To alleviate these problems, we propose a client-based architecture that incorporates noun phrasing and self-organizing map techniques. Two systems, namely CI Spider and Meta Spider, have been built based on this architecure. User evaluation studies have been conducted and the findings suggest that the proposed architecture can effectively facilitate web search and analysis.} } @INPROCEEDINGS{Witten01 ,AUTHOR = "Ian H. Witten and David Bainbridge and Stefan J. Boddie" ,TITLE = "Power to the People: End-user Building of Digital Library Collections" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {Naturally, digital library systems focus principally on the reader: the consumer of the material that constitutes the library. In contrast, this paper describes an interface that makes it easy for people to build their own library collections. Collections may be built and served locally from the user's own web server, or (given appropriate permissions) remotely on a shared digital library host. End users can easily build new collections styled after existing ones from material on the Web or from their local files - or both, and collections can be updated and new ones brought on-line at any time. The interface, which is intended for non-professional end users, is modeled after widely used commercial software installation packages. Lest one quail at the prospect of end users building their own collections on a shared system, we also describe an interface for the administrative user who is responsible for maintaining a digital library installation.} } @INPROCEEDINGS{Myers01 ,AUTHOR = "Brad A. Myers and Juan P. Casares and Scott Stevens and Laura Dabbish and Dan Yocum and Albert Corbett" ,TITLE = "A Multi-View Intelligent Editor for Digital Video Libraries" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {Silver is an authoring tool that aims to allow novice users to edit digital video. The goal is to make editing of digital video as easy as text editing. Silver provides multiple coordinated views, including project, source, outline, subject, storyboard, textual transcript and timeline views. Selections and edits in any view are synchronized with all other views. A variety of recognition algorithms are applied to the video and audio content and then are used to aid in the editing tasks. The Informedia Digital Library supplies the recognition algorithms and metadata used to support inelligent editing, and Informedia also provides search and a repository. The metadata includes shot boundaries and a time-synchronized transcript, which are used to support intelligent selection and intelligent cut/copy/paste} } @INPROCEEDINGS{Wacholder01 ,AUTHOR = "Nina Wacholder and David K. Evans and Judith L. Klavans" ,TITLE = "Automatic Identification and Organization of Index Terms for Interactive Browsing" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {The potential of automatically generated indexes for information access has been recognized for several decades (e.g., Bush 1945, Edmundson and Wyllys, 1961), but the quantity of text and the ambiguity of natural language processing have made progress at this task more difficult than was originally foreseen. Recently, a body of work on development of interactive systems to support phrase browsing has begun to emerge (e.g., Anick and Vaithyanathan 1997, Gutwin et al., Nevill-Manning et al. 1997, Godby and Reighart 1998). In this paper, we consider two issues related to the use of automatically identified phrases as index terms in a dynamic text browser (DTB), a user-centered system for navigating and browsing index terms: 1) What criteria are useful for assessing the usefulness of automatically identified index terms? and 2) Is the quality of the erms identified by automatic indexing such that they provide useful access to document content?} } @INPROCEEDINGS{Jones01 ,AUTHOR = "Steve Jones and Gordon W. Paynter" ,TITLE = "Human Evaluatin of Kea, an Automatic Keyphrasing System" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {This paper describes an evaluation of the Kea automatic keyphrase extraction algorithm. Tools that automatically identify keyphrases are desirale because document keyphrases have numerous applications in digital library sysems, but are costly and time consuming to manually assign. Keyphrase extraction algorithms are usually evaluated by comparison to author-specified keywords, but this methodology has several well-known shortcomings. The results presented in this pper are based on subjective evaluations of the quality and appropriateness of keyphrases by human assessors, and make a number of contributions. First they validate previous evaluations of Kea that rely on author keywords. Second, they show Kea's performance is comparable to that of similar systems that have been evaluated by human assessors. Finally, they justify the use of author keyphrases as a performance metric by showing that authors generally choose good keywords.} } @INPROCEEDINGS{Khoo01 ,AUTHOR = "Michael Khoo" ,TITLE = "Community Design of DLESE's Collections Review Policy: A Technological Frames Analysis" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {In this paper, I describe the design of a collection review policy for the Digital Library for Earth System Education (DLESE). A distinctive feature of DLESE as a digital library is the 'DLESE community,' composed of voluntary members who contribute metadata and resource reviews to DLESE. As the DLESE community is open, the question of how to evaluate community contributions is a crucial part of the review policy design process. In this paper, technological frames theory is used to analyse this design process by looking at how the designers work with two differing definitions of the 'peer reviewer,' (a) per reviewer as arbiter or editor, and (b) peer reviewer as colleague. Content analysis of DLESE documents shows that these frames can in turn be related to two definitions that DLESE offers of itself: DLESE as a library, and DLESE as a digital artifact. The implications of the presence of divergent, technological frames for the design process are summarised, and some suggestions for future research are outlined.} } @INPROCEEDINGS{Muir01 ,AUTHOR = "Adrienne Muir" ,TITLE = "Legal Deposit of Digital Publications: A Review of Research and Development Activity" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {There is a global trend towards extending legal deposit to include digital publications in order to maintain comprehensive national archives. However, including digital publications in legal deposit regulation is not enough to ensure the long-term preservation of these publications. Concepts, principles and practices accepted and understood in the print environment, may have new meanings or no longer be appropriate in a networked environment. Mechanisms for identifying, selecting and depositing digital material either do not exist, or are inappropriate, for some kinds of digital publication. Work on developing digital preservation strategies is at an early stage. National and other deposit libraries are at the forefront of research and development in this area, often working in partnership with other libraries, publishers and technology vendors. Most work is of a technical nature. There is some work on developing policies and strategies for managing digital resources. However, not all management issues or users needs are being addressed.} } @INPROCEEDINGS{Blandford01 ,AUTHOR = "Ann Blandford and Hanna Stelmaszewska and Nick Bryan-Kinns" ,TITLE = "Use of Multiple Digital Libraries: A Case Study" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {The aim of the work reported here was to better understand the usability issues raised when digital libraries are used in a natural setting. The method used was a protocol analysis of users working on a task of their own choosing to retrieve documents from publicly available digital libraries. Various classes of usability difficulties were found. Here, we focus on use in context -- that is, usability concerns that arise from the fact that libraries are accessed in particular ways, under technically and organisationally imposed constraints, and that use of any particular resource is discretionary. The concepts from an Interaction Framework, which provides support for reasoning about patterns of interaction between users and systems, are applied to understand interaction issues.} } @INPROCEEDINGS{Cunningham01 ,AUTHOR = "Sally Jo Cunningham and Chris Knowles and Nina Reeves" ,TITLE = "An Ethnographic Study of Technical Support Workers: Why We Didn't Build a Tech Support Digital Library" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {In this paper we describe the results of an ethnographic study of the information behaviours of university technical support workers and their information needs. The study looked at how the group identified, located and used information from a variety of sources to solve problems arising in the course of their work. The results of the investigation are discussed in the context of the feasibility of developing a potential information base that could be used by all members of the group. Whilst a number of their requirements would easily be fulfilled by the use of a digital library, other requirements would not. The paper illustrates the limitations of a digital library with respect to the information behaviours of this group of subjects and focuses on why a digital library would not appear to be the ideal support tool for their work.} } @INPROCEEDINGS{Green01 ,AUTHOR = "Noah Green and Panagiotis G. Ipeirotis and Luis Gravano" ,TITLE = "SDLIP + STARTS = SDARTS: A Protocol and Toolkit for Metasearching" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {In this paper we describe how we combined SDLIP and STARTS, two complementary protocols for searching over distributed document collections. The resulting protocol, which we call SDARTS, is simple yet expressible enough to enable building sophisticated metasearch engines. SDARTS can be viewed as an instantiation of SDLIP with metasearch-specific elements from STARTS. We also report on our experience building three SDARTS-compliant wrappers: for locally available plain-text document collections, for locally available XML document collections, and for external web-accessible collections. These wrappers were developed to be easily customizable for new collections. Our work was developed as part of Columbia University's Digital Libraries Initiative-Phase 2 (DLI2) project, which involves the departments of Computer Science, Medical Informatics, and Electrical Engineering, the Columbia University libraries, and a large number of industrial partners. The main goal of the project is to provide personalized access to a distributed patient-care digital library.} } @INPROCEEDINGS{Yu01 ,AUTHOR = "Clement Yu and Prasoon Sharma and Weiyi Meng and Yan Qin" ,TITLE = "Database Selection for Processing k Nearest Neighbors Queries in Distributed Environments" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {We consider the processing of digital library queries, consisting of a text component and a structured component in distributed environments. The text component can be processed using techniques given in previous papers. In this paper, we concentrate on the processing of the structured component of a distributed query. Histograms are constructed and algorithms are given to provide estimates of the desirabilities of the databases with respect to the given query. Databases are selected in descending order of desirability. An algorithm is also given to select tuples from the selected databases. Experimental results are given to show that the techniques provided here are effective and efficient.} } @INPROCEEDINGS{CooperJ01 ,AUTHOR = "James W. Cooper and Mahesh Viswanathan and Donna Byron and Margaret Chan" ,TITLE = "Building Searchable Collections of Enterprise Speech Data" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {We have applied speech recognition and text-mining technologies to a set of recorded outbound marketing calls and analyzed the results. Since speaker-independent speech recognition technology results in a significantly lower recognition rate than that found when the recognizer is trained for a particular speaker, we applied a number of post-processing algorithms to the output of the recognizer to render it suitable for the Textract text mining system. We indexed the call transcripts using a search engine and used Textract and associated Java technologies to place the relevant terms for each document in a relational database. Following a search query, we generated a thumbnail display of the results of each call with the salient terms highlighted. We illustrate these results and discuss their utility. We took the results of these experiments and continued this analysis on a set of talks and presentations. We describe a distinct document genre based on the note-taking concept of document content, and propose a significant new method for measuring speech recognition accuracy. This procedure is generally relevant to the problem of capturing meetings and talks and providing a searchable index of these presentations on the web.} } @INPROCEEDINGS{Byrd01 ,AUTHOR = "Donald Byrd" ,TITLE = "Music-Notation Searching and Digital Libraries" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {Almost all work on music information retrieval to date has concentrated on music in the audio and event (normally MIDI) domains. However, music in the form of notation, expecially Conventional Music Notation (CMN), is of much interest to musically-trained persons, both amateurs and professionals, and searching CMN has great value for digital music libraries. One obvious reason little has been done on music retrieval in CMN form is the overwhelming complexity of CMN, which requires a very substantial investment in programming before one can even begin studying music IR. This paper reports on work adding music-retrieval capabilities to Nightingale, an existing professional-level music-notation editor.} } @INPROCEEDINGS{Geffet01 ,AUTHOR = "Maayan Geffet and Dror G. Feitelson" ,TITLE = "Hierarchical Indexing and Document Matching in BoW" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {BoW is an on-line bibliographical repository based on a hierarchical concept index to which entries are linked. Searching in the repository should therefore return matching topics from the hierarchy, rather than just a list of entries. Likewise, when new entries are inserted, a search for relevant topics to which they should be linked is required. We develop a vector-based algorithm that creates keyword vectors for the set of competing topics at each node in the hierarchy, and show how its performance improves when domain-specific features are added (such as special handling of topic titles and author names). The results of a 7-fold cross validation on a corpus of some 3,500 entries with a 5-level index are hit ratios in the range of 89-95%, and most of the misclassifications are indeed ambiguous to begin with.} } @INPROCEEDINGS{Wang01 ,AUTHOR = "James Z. Wang and Yanping Du" ,TITLE = "Scalable Integrated Region-based Image Retrieval using IRM and Statistical Clustering" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {Statistical clustering is critical in designing scalable image retrieval systems. In this paper, we present a scalable algorithm for indexing and retrieving images based on region segmentation. The method uses statistical clustering on region features and IRM (Integrated Region Matching), a measure developed to evaluate overall similarity between images that incorporates properties of all the regions in the images by a region-matching scheme. Compared with retrieval based on individual regions, our overall similarity approach (a) reduces the influence of inaccurate segmentation, (b) helps to clarify the semantics of a particular region, and (c) enbables a simple querying interface for region-based image retrieval systems. The algorithm has been implemented as a part of our experimental SIMPLIcity image retrieval system and tested on large-scale image databases of both general-purpose images and pathology slides. Experiments have demonstrated that this technique maintains the accuracy and robustness of the original system while reducing the matching time significantly.} } @INPROCEEDINGS{Nanard01 ,AUTHOR = "Marc Nanard and Jocelyne Nanard" ,TITLE = "Cumulating and Sharing End Users Knowledge to Improve Video Indexing in a Video Digital Library" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {In this paper, we focus on a user driven approach to improve video indexing. It consists in cumulating the large amount of small, individual efforts done by the users who access information, and to provide a community management mechanism to let users share the elicited knowledge. This technique is currently being developed in the "OPALES" environment and tuned up at the "Institut National de l'Audiovisuel" (INA), a National Video Library in Paris, to increase the value of its partimonial video archive collections. It relies on a portal providing private workspaces to end users, so that a large part of their work can be shared between them. The effort for interpreting documents is directly done by the expert users who work for their own job on the archives. OPALES provides an original notion of "point of view" to enable the elicitation and the sharing of knowledge between communities of users, without leading to messy structures. The overall result consists in linking exportable private metadata to archive documetns and managing the sharing of the elicited knowledge between users communities.} } @INPROCEEDINGS{Christel01 ,AUTHOR = "Michael G. Christel and Bryan Maher and Andrew Begun" ,TITLE = "XSLT for Tailored Access to a Digital Video Library" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {Surrogates, summaries, and visualizations have been developed and evaluated for accessing a digital video library containing thousands of documents and terabytes of data. These interfaces, formerly implemented within a monolithic stand-alone application, are being migrated to XML and XSLT for delivery through web browsers. The merits of these interfaces are presented, along with a discussion of the benefits in using W3C recommendations such as XML and XSLT for delivering tailored access to video over the web.} } @INPROCEEDINGS{Ben01 ,AUTHOR = "Jezekiel Ben-Arie and Purvin Pandit and ShyamSundar Rajaram" ,TITLE = "Design of A Digital Library for Human Movement" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {This paper is focused on a central aspect in the design of our planned digital library for human movement, i.e. on the aspect of representation and recognition of human activity from video data. The method of representation is important since it has a major impact on the design of all the other building blocks of our system such as the user interface/query block or the activity recognition/storage block. In this paper we evaluate a representation method for human movement that is based on sequences of angular poses and angular velocites of the human skeletal joints, for storage and retrieval of human actions in video databases. The choice of a representation method plays an important role in the database structure, search methods, storage efficiency etc.. For this representation, we develop a novel approach for complex human activity recognition by employing multidimensional indexing combined with temporal or sequential correlation. this scheme is then evaluated with respect to its efficiency in storage and retrieval. For the indexing we use postures of humans in videos that are decomposed into a set of multidimensional tuples which represent the poses/velocities of human body parts such as arms, legs and torso. Three novel methods for human activity recognition are theoretically and experimentally compared. The methods require only a few sparsely sampled human postures. We also achieve speed invariant recognition of activities by eliminating the time factor and replacing it with sequence information. The indexing approach also provides robust recognition and an efficient storage/retrieval of all the activities in a small set of hash tables.} } @INPROCEEDINGS{Dong01 ,AUTHOR = "Andy Dong and Alice M. Agogino" ,TITLE = "Design Principles for the Information Architecture of a SMET Education Digital Library" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {This implementation paper introduces principles for the information architecture of an educational digital library, principles that address the distinction between designing digital libraries for education and designing digital libraries for information retrieval in general. Design is a key element of any successful product. Good designers and their designs put technology into the hands of the user, making the produc'ts focus comprehensible and tangible through design. As straightforward as this may appear, the design of learning technologies is often masked by the enabling technology. In fact, they often lack an explicitly stated instructional design methodology. While the technologies are important hurdles to overcome, we advocate learning systems that empower education-driven experiences rather than technology-driven experiences. This work describes a concept for a digital library for science, mathematics, engineering and technology education (SMETE), a library with an information architecture designed to meet learners' and educators' needs. Utilizing a constructivist model of learning, the authors present practical approaches to implementing the information architecture and it technology underpinnings. The authors propose the specifications for the information architecture and a visual design of a digital library for communicating learning to the audience. The design methodology indicates that a scenario-driven design technique sensitive to the contextual nature of learning offers a useful framework for tailoring technologies that help empower, not hinder, the educational sector.} } @INPROCEEDINGS{Kang01 ,AUTHOR = "ByungHoon Kang and Robert Wilensky" ,TITLE = "Toward a Model of Self-administering Data" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {We describe a model of self-administering data. In this model, a declarative description of how a data object should behave is attached to the object, either by a user or by a data input device. A widespread infrastructure of self-administering data handlers is presumed to exist; these handlers are responsible for carrying out the specifications attached to the data. Typically, the specifications express how and to whom the data should be transferred, how it should be incorporated when it is received, what rights recipients of the data will have with respect toit, and the kind of relation that should exist between distributed copies of the object. Functions such as distributed version control can be implemented on top of the basic handler functions. We suggest that this model can provide superior support for common cooperative functions. Because the model is declarative, users need only express their intentions once in creating a self-administering description, and need not be concerned with manually performing subsequent repetitious operations. Because the model is peer-to-per, users are less dependent on additional, perhaps costly resources, at least when these are not critical. An initial implementation of the model has been created. We are experimenting with the model both as a tool to aid in digital library functions, and as a possible replacement for some server oriented functions.} } @INPROCEEDINGS{McKeown01 ,AUTHOR = "Kathleen R. McKeown and Shih-Fu Chang and James Cimino and Steven K. Feiner and Carol Friedman and Luis Gravano and Vasileios Hatzivassiloglou and Steven Johnson and Desmond A. Jordan and Judith L. Klavans and Andre Kushniruk and Vimla Patel and Simone Teufel" ,TITLE = "PERSIVAL, a System for Personalized Search and Summarization over Multimedia Healthcare Information" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {In healthcare settings, patients need access to online information that can help them understand their medical situation. Physicians need information that is clinically relevant to an individual patient. In this paper, we present our progress on developing a system, PERSIVAL, that is designed to provide personalized access to a distributed patient care digital library. Using the secure, online patient records at New York Presbyterian Hospital as a user model, PERSIVAL's components tailor search, presentation and summarization of online multimedia information to both patients and healthcare providers.} } @INPROCEEDINGS{Lorie01 ,AUTHOR = "Raymond A. Lorie" ,TITLE = "Long Term Preservation of Digital Information" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {The preservation of digital data for the long term presents a variety of challenges from technical to social and organization. The technical challenge is to ensure that the information, generated today, can survive long term changes in storage media, devices and data formats. This paper presents a novel approach to the problem. It distinguishes between archiving of data files and archiving of programs (so that their behavior may be reenacted in the future). For the archiving of a data file, the proposal consists of specifying the processing that needs to be performed on the data (as physically stored) in order to return the information to a future client (according to a logical view of the data). The process specification and the logical view definition are archived with the data. For the archiving of a program behavior, the proposal consists of saving the original executable object code together with the specificaiton of the processing that needs to be performed for each machine instruction of the original computer (emulation). In both cases, the processing specificatio is based on a Universal Virtual Computer that is general, yet basic enough as to remain relevant in the future.} } @INPROCEEDINGS{Cooper01 ,AUTHOR = "Brian Cooper and Hector Garcia-Molina" ,TITLE = "Creating Trading Networks of Digital Archives" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {Digital archives can best survive failures if they have made several copies of their collections at remote sites. In this paper, we discuss how autonomous sites can cooperate to provide preservation by trading data. We examine the decisions that an archive must make when forming trading networks, such as the amount of storage space to provide and the best number of partner sites. We also deal with the fact that some sites may be more reliable than others. Experimental results from a data trading simulator illustrate which policies are most reliable. Our techniques focus on preserving the ``bits'' of digital collections; other services that focus on other archiving concerns (such as preserving meaningful metadata) can be built on top of the system we describe here.} } @INPROCEEDINGS{Crespo01 ,AUTHOR = "Arturo Crespo and Hector Garcia-Molina" ,TITLE = "Cost-Driven Design for Archival Repositories" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {Designing an archival repository is a complex task because there are many alternative configurations, each with different reliability levels and costs. In this paper we study the costs involved in an Archival Repository and we introduce a design framework for evaluating alternatives and choosing the best configuration in terms of reliability and cost. We also present a new version of our simulation took, ArchSim/C that aids in the decision process. The design framework and the usage of ArchSim/C are illustrated with a case study of a hypothetical (yet realistic) archival repository shared between two universities.} } @INPROCEEDINGS{Faensen01 ,AUTHOR = "D. Faensen and L. Faulstich and H. Schweppe and A. Hinze and A. Steidinger" ,TITLE = "Hermes - A Notification Service for Digital Libraries" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {The high publication rate of scholarly material makes searching and browsing an inconveninet way to keep oneself up-to-date. Instead of being the active part in information access, researchers want to be notified whenever a new paper in one's research area is published. While more and more publishing houses or portal sites offer notification services this approach has several disadvantages. We introduce the Hermes alerting service, a service that integrates a variety of different information providers making their heterogeneity transparent for the users. Hermes offers sophisticated filtering capabilities preventing the user from drowning in a flood of irrelevant information. From the user's point of view it integrates the providers into a single source. Its simple provider interface makes it easy for publishers to join the service and thus reaching the potential readers directly. This paper presents the architecture of the Hermes service and discusses the issues of heterogeneity of information sources. Furthermore, we discuss the benefits and disadvantages of message-oriented middleware for implementing such a service for digital libraries.} } @INPROCEEDINGS{riggs01 ,AUTHOR = "Tracy Riggs and Robert Wilensky" ,TITLE = "An Algorithm for Automated Rating of Reviewers" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {The current system for scholarly information dissemination may be amenable to significant improvement. In particular, going from the current system of journal publication to one of self-distributed documents offers significant cost and timeliness advantages. A major concern with such alternatives is how to provide the value currently afforded by the peer review system. Here we propose a mechanism that could plausibly supply such value. In the peer review system, papers are judged meritorious if good reviewers give them good reviews. In its place, we propose a collaborative filtering algorithm which automatically rates reviews, and incorporates the quality of the reviewer into the metric of merit for the paper. Such a system seems to provide all the benefits of the current peer review system, while at the same time being much more flexible. We have implemented a number of parameterized variations of this algorithm, and tested them on data available from a quite different application. Our initial experiments suggest that the algorithm is in fact ranking reviewers reasonably.} } @INPROCEEDINGS{marisa01 ,AUTHOR = "Richard J. Marisa" ,TITLE = "HeinOnline: An Online Archive of Law Journals" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {HeinOnline is a new online archive of law journals. Development of HeinOnline began in late 1997 through the cooperation of Cornell Information Technologies, William S. Hein & Co., Inc. of Buffalo, NY., and the Cornell Law Library. Built upon the familar Dienst and new Open Archive Initiative protocols, HeinOnline extends the reliable and well-established management practices of open access archives like NCSTRL and CoRR to a subscription-based collection. The decisions made in creating HeinOnline. Dienst architectural extensions, and issues which have arisen during operation of HeinOnline are described.} } @INPROCEEDINGS{druin01 ,AUTHOR = "Allison Druin and Benjamin B. Bederson and Juan Pablo Hourcade and Lisa Sherman and Glenda Revelle and Michele Platner and Stacy Weng" ,TITLE = "Designing a Digital Library for Young Children: An Intergenerational Partnership" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {As more information resources become accessible using computers, our digital interfaces to those resources need to be appropriate for all people. However when it comes to digital libraries, the interfaces have typically been designed for older children or adults. Therefore, we have begun to develop a digital library interface developmentally appropriate for young children (ages 5-10 years old). Our prototype system we now call "SearchKinds" offers a graphical interface for querying, browsing and reviewing search results. This paper describes our motifation for the research, the design partnership we established between children and adults, our design process, the technology outcomes of our current work, and the lessons we have learned.} } @INPROCEEDINGS{theng01 ,AUTHOR = "Yin Leng Theng and Norliza Mohd-Nasir and George Buchanan and Bob Fields and Harold Thimbleby and Noel Cassidy" ,TITLE = "Dynamic Digital Libraries for Children" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {The majority of current digital libraries (DLs) are not designed for children. For DLs to be popular with children, they need to be fun, easy-to-use and empower them, whether as readers or authors. This paper describes a new children's DL emphasizing its design and evaluation, working with the children (11-14 year olds) as design partners and testers. A truly participatory process was used, and observational study was used as a means of refinement to the initial design of the DL prototype. In constrast with current DLs, the children's DL provides both a static as well as a dynamic environment to encourage active engagement of children in using it. Design, implementation and security issues are also raised.} } @INPROCEEDINGS{sumner01 ,AUTHOR = "Tamara Sumner and Melissa Dawe" ,TITLE = "Looking at Digital Library Usability from a Reuse Perspective" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {The need for information systems to support the dissemination and reuse of educational resources has sparked a number of large-scale digital library efforts. This article describes usability findings from one such project - the Digital Library for Earth System Education (DLESE) - focusing on its role in the process of educational resource reuse. Drawing upon a reuse model developed in the domain of software engineering, the reuse cycle is broken down into five stages: formulation of a reuse intention, location, comprehension, modification, and sharing. Using this model to analyze user studies in the DLESE project, several implications for library system design and library outreach activities are highlighted. One finding is that resource reuse occurs at different stages in the educational design process, and each stage imposes different and possibly conflicting requirements on digital library design. Another finding is that reuse is a distributed process across several artifacts, both within and outside of the library itself. In order for reuse to be successful, a usability line cannot be drawn at the library boundary, but instead must encompass both the library system and the educational resources themselves.} } @INPROCEEDINGS{crane01 ,AUTHOR = "Gregory Crane and David A. Smith and Clifford E. Wulfman" ,TITLE = "Building a Hypertextual Digital Library in the Humanities: A Case Study on London" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {This paper describes the creation of a new humanities digital library collection: 11,000,000 words and 10,000 images representing books, images and maps on pre-twentieth century London and its environs. The London collection contained far more dense and precise information than the materials from the Grecco-Roman world on which we had previously concentrated. The London collection thus allowed us to explore new problems of data structure, manipulation, and visualization. This paper contrasts our model for how humanities digital libraries are best used with the assumptions that underlie many academic digital libraries on the one hand and more literary hypertexts on the other. Since encoding guidelines such as those from the TEI provide collection designers with far more options than any one project can realize, this paper describes what structures we used to organize the collection and why. We particularly emphasize the importance of mining historical "authority lists" (encyclopedias, gazetteers, etc.) and then generating automatic "span-to-span" links within the collection. } } @INPROCEEDINGS{brown01 ,AUTHOR = "Michael S. Brown and W. Brent Seales" ,TITLE = "The Digital Atheneum: New Approaches for Preserving, Restoring and Analyzing Damaged Manuscripts" ,BOOKTITLE = jcdl01 ,YEAR = "2001" ,entered-by = "Rebecca Wesley" ,abstract = {This paper presents research focused on developing new techniques and algorithms for the digital acquisition, restoration, and study of damaged manuscripts. We present results from an acquisition effort in partnership with the British Library, funded through the NSF DLI-2 program, designed to capture 3-D models of old and damaged manuscripts. We show how these 3-D facsimiles can be analyzed and manipulated in ways that are tedious or even impossible if confined to the physical manuscript. In particular, we present results from a restoration framework we have developed for flattening the 3-D representation of badly warped manuscripts. We expect these research directions to give scholars more sophisticated methods to preserve, restore, and better understand the physical objects they study.} } @INPROCEEDINGS{Tibbo02 ,AUTHOR = "Helen R. Tibbo" ,TITLE = "Primarily History: Historians and the Search for Primary Source Materials" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544222)" ,entered-by = "Rebecca Wesley" ,abstract = {This paper describes the first phase of an international project that is exploring how historians locate primary resource materials in the digital age, what they are teaching their Ph.D. students about finding research materials, and what archivists are doing to facilitate access to these materials. Preliminary findings are presented from a survey of 300 historians studying American History from leading institutions of higher education in the U.S. Tentative conclusions indicate the need to provide multiple pathways of access to historical research materials including paper-based approaches and newer digital ones. The need for user education, especially in regard to electronic search methodologies is indicated.} } @INPROCEEDINGS{Droettboom02 ,AUTHOR = "Michael Droettboom and Karl MacMillan and Iciro Fujinaga and G. Sayeed Choudhury and Tim DiLauro and Mark Patton and Teal Anderson" ,TITLE = "Using the Gamera Framework for the Recognition of Cultural Heritage Materials" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544223)" ,abstract = {This paper presents a new toolkit for the creation of customized structured document recognition applications by domain experts. This open- source system, called Gamera, allows a user, with particular knowledge of the documents to be recognized, to combine image processing and recognition tools in an easy to use, interactive, graphical scripting environment. Gamera is one of the key technology components in a proposed international project for the digitization of diverse types of humanities documents.} } @INPROCEEDINGS{Gustman02 ,AUTHOR = "Samuel Gustman and Dagobert Soergel and Douglas Oard and William Byrne and Michael Picheny and Bhuvana Ramabhadran and Douglas Greenberg" ,TITLE = "Supporting Access to Large Digital Oral History Archives" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544224)" ,abstract = {This paper, describes our experience with the creation, indexing and providing access to a very large archive of videotaped oral histories- 116,000 hours of digitized interviews in 32 languages from 52,000 survivors, liberators, rescuers and witnesses of the Nazi Holocaust-and identifies a set of critical research issues in user requirement studies, automatic speech recognition, automatic classification, segmentation, and summarization, retrieval, and user interfaces that must be addressed if we are to provide full and detailed access to collections of this size.} } @INPROCEEDINGS{McDonald02 ,AUTHOR = "Daniel McDonald and Hsinchun Chen" ,TITLE = "Using Sentence-Selection Heuristics to Rank Text Segments in TXTRACTOR" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:DOIhttp://doi.acm.org/10.1145/544220.544226)" ,abstract = {TXTRACTOR is a tool that uses established sentence-selection heuristics to rank text segments, producing summaries that contain a user-defined number of sentences. We hypothesize that ranking text segments via traditional sentence-selection heuristics produces a balanced summary with more useful information than one produced by using segmentation alone. The proposed summary is created in a three-step process, which includes 1) sentence evaluation 2) segment identification and 3) segment ranking. As the required length of the summary changes, low-ranking segments can then be dropped from (or higher ranking segments added to) the summary. We compare the output of TXTRACTOR to the output of a segmentation tool based on the TextTiling algorithm to validate the approach.} } @INPROCEEDINGS{Kan02 ,AUTHOR = "Min-Yen Kan and Judith L. Klavans" ,TITLE = "Using Librarian Techniques in Automatic Text Summarization for Information Retrieval" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544227)" ,abstract = {A current application of automatic text summarization is to provide an overview of relevant documents coming from an information retrieval (IR) system. This paper examines how Centrifuser, one such summarization system, was designed with respect to methods used in the library community. We have reviewed these librarian expert techniques to assist information seekers and codified them into eight distinct strategies. We detail how we have operationalized six of these strategies in our computational system and present a preliminary evaluation.} } @INPROCEEDINGS{Pinto02 ,AUTHOR = " David Pinto and Michael Branstein and Ryan Coleman and Matthew King and Wei Li, Xing Wei and W. Bruce Croft" ,TITLE = "QuASM: A System for Question Answering Using Semi-Structured Data" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:DOIhttp://doi.acm.org/10.1145/544220.544228)" ,abstract = {This paper describes a system for question answering using semi-structured metadata, QuASM (pronounced "chasm"). Question answering systems aim to improve search performance by providing users with specific answers, rather than having users scan retrieved documents for these answers. Our goal is to answer factual questions by exploiting the structure inherent in documents found on the World Wide Web (WWW). Based on this structure, documents are indexed into smaller units and associated with metadata. Transforming table cells into smaller units associated with metadata is an important part of this task. In addition, we report on work to improve question classification using language models. The domain used to develop this system is documents retrieved from a crawl of www.fedstats.gov.} } @INPROCEEDINGS{Marshall02 ,AUTHOR = "Catherine C. Marshall and Christine Ruotolo" ,TITLE = "Reading-in-the-Small: A Study of Reading on Small Form Factor Devices" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544230)" ,abstract = {The growing ubiquity of small form factor devices such as Palm Pilots and Pocket PCs, coupled with widespread availability of digital library materials and users' increasing willingness to read on the screen, raises the question of whether people can and will read digital library materials on handhelds. We investigated this question by performing a field study based on a university library's technology deployment in an academic environment: two classes were conducted using materials that were available in e-book format on Pocket PCs in addition to other electronic and paper formats. The handheld devices, the course materials, and technical support were all provided to students in the courses to use as they saw fit. We found that the handhelds were a good platform for reading secondary materials, excerpts, and shorter readings; they were used in a variety of circumstances where portability is important, including collaborative situations such as the classroom. We also discuss the effectiveness of annotation, search, and navigation functionality on the small form factor devices. We conclude by defining a set of focal areas and issues for digital library efforts designed for access by handheld computers.} } @INPROCEEDINGS{Huang02 ,AUTHOR = "Zan Huang and Wingyan Chung and Thian-Huat Ong and Hsinchun Chen" ,TITLE = "A Graph-based Recommender System for Digital Library" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544231)" ,abstract = {Research shows that recommendations comprise a valuable service for users of a digital library. While most existing recommender systems rely either on a purely content-based approach or purely collaborative approach to make recommendations, there is a need for digital libraries to use a combination of both approaches (a hybrid approach) to improve recommendations. In this paper, we report how we tested the idea of using a graph-based recommender system that naturally combines the content-based and collaborative approaches. Due to the similarity between our problem and a concept retrieval task, a Hopfield net algorithm was used to exploit high-degree book-book, user-user and book-user associations. Sample hold-out testing and preliminary subject testing were conducted to evaluate the system, by which it was found that the system gained improvement with respect to both precision and recall by combining content-based and collaborative approaches. But no significant improvement was observed by exploiting high-degree associations.} } @INPROCEEDINGS{Kelly02 ,AUTHOR = "Diane Kelly and Colleen Cool" ,TITLE = "The Effects of Topic Familiarity on Information Search Behavior" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544232)" ,abstract = {We describe results from a preliminary investigation of the relationship between topic familiarity and information search behavior. Two types of information search behaviors are considered: reading time and efficacy. Our results indicate that as one's familiarity with a topic increases, one's searching efficacy increases and one's reading time decreases. These results suggest that it may be possible to infer topic familiarity from information search behavior.} } @INPROCEEDINGS{Harper02 ,AUTHOR = "David J Harper and Sara Coluthard and Raja Kalpana and Sun Yixing" ,TITLE = "A Language Modelling Approach to Relevance Profiling for Document Browsing" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544234)" ,abstract = {This paper describes a novel tool, SmartSkim, for content-based browsing or skimming of documents. The tool integrates concepts from passage retrieval and from interfaces, such as TileBars, which provide a compact overview of query term hits within a document. We base our tool on the concept of relevance profiling, in which a plot of retrieval status values at each word position of a document is generated. A major contribution of this paper is applying language modelling to the task of relevance profiling. We describe in detail the design of the SmartSkim tool, and provide a critique of the design. Possible applications of the tool are described, and we consider how an operational version of SmartSkim might be architected.} } @INPROCEEDINGS{Tudhope02 ,AUTHOR = "Douglas Tudhope and Ceri Binding and Dorothee Blocks and Daniel Cunliffe" ,TITLE = "Compound Terms In Context: A Matching Function For Search Thesauri" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544235)" ,abstract = {In faceted thesauri, application guidelines encourage the synthesis of individual terms when indexing. These faceted compound strings have potential for high precision in retrieval. However, the lack of flexible retrieval tools that yield ranked matches of strings hinders the application of thesauri and related Knowledge Organization Systems to domains requiring precision in searching. Previous work has tended to approach the problem as involving unstructured lists. This paper extends the notion of similarity between strings of terms by considering the possibilities afforded by faceted thesauri, focusing on the Art and Architecture Thesaurus. The work reported is part of the ongoing 'FACET' project in collaboration with the National Museum of Science and Industry and its collections database. The paper discusses a matching function for faceted subject headings that does not rely on exact matching but incorporates term expansion via a measure of semantic closeness. Ranked results are produced for strings of terms that take account of facet structure and deal intuitively with missing or partially matching terms.} } @INPROCEEDINGS{Vieira02 ,AUTHOR = " Rodrigo C. Vieira and Pavel Calado and Altigran S. Silva and Alberto H. F. Laender and Berthier A. Ribeiro-Neto" ,TITLE = "Structuring Keyword-Based Queries for Web Databases" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544236)" ,abstract = {This paper describes a framework, based on Bayesian belief networks, for querying Web databases using keywords only. According to this framework, the user inputs a query through a simple search-box interface. From the input query, one or more plausible structured queries are derived and submitted to Web databases. Since the query structuring is done automatically, the resulting queries might be imprecise (i.e., they may do not match exactly a structured query built manually). The results are then retrieved and presented to the user as ranked answers. To evaluate our framework, an experiment using 38 example queries was carried out. We found out that 97s% of the time, one of the top three resulting structured queries is the proper one. Further, when the user selects one of these three top queries for processing, the ranked answers present average precision figures of 92%.} } @INPROCEEDINGS{Cui02 ,AUTHOR = "Hong Cui and P. Bryan Heidorn and Hong Zhang" ,TITLE = "An Approach to Automatic Classification of Text for Information Retrieval" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544237)" ,abstract = {In this paper, we explore an approach to make better use of semi-structured documents in information retrieval in the domain of biology. Using machine learning techniques, we make those inherent structures explicit by XML markups. This marking up has great potentials in improving task performance in specimen identification and the usability of online flora and fauna.} } @INPROCEEDINGS{Norris02 ,AUTHOR = "Cathie Norris and Elliot Soloway and June M. Abbas" ,TITLE = "Middle School Children's Use of the ARTEMIS Digital Library" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544239)" ,abstract = {Middle school student's interaction within a digital library is explored. Research into the differential use of interface features by students is presented. Issues of representation and retrieval obstacles are examined. A mechanism for evaluating user's search terms and questions is explained. Findings of current research indicate that student's interaction with the system varied between individual classes and between different achievement levels. Terms used by the system to represent the resources do not adequately represent the user groups' information needs.} } @INPROCEEDINGS{Weatherley02 ,AUTHOR = "John Weatherley and Tamara Sumner and Michael Khoo and Michael Wright and Marcel Hoffman" ,TITLE = "Partnership Reviewing: A Cooperative Approach for Peer Review of Complex Educational Resources" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544240)" ,abstract = {Review of digital educational resources, such as course modules, simulations, and data analysis tools, can differ from review of scholarly articles, in the heterogeneity and complexity of the resources themselves. The Partnership Review Model, as demonstrated in two cases, appears to promote cooperative interactions between distributed resource reviewers, enabling reviewers to effectively divide up the task of reviewing complex resources with little explicit coordination. The shared structural outline of the resource made visible in the review environment enables participants to monitor other reviewers' actions and to thus target their efforts accordingly. This reviewing approach may be effective in educational digital libraries that depend on community volunteers for most of their reviewing.} } @INPROCEEDINGS{Chua02 ,AUTHOR = " Lian-Heong Chua and Dion Hoe-Lian Goh and Ee-Peng Lim and Zehua Liu and Rebecca Pei-Hui Ang" ,TITLE = "A Digital Library For Geography Examination Resources" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544241)" ,abstract = {We describe a Web-based application developed above a digital library of geographical resources for Singapore students preparing to take a national examination in geography. The application provides an interactive, non-sequential approach to learning that supplements textbooks.} } @INPROCEEDINGS{McMartin02 ,AUTHOR = " Flora McMartin and Youki Terada" ,TITLE = "Digital Library Services for Authors of Learning Materials" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544242)" ,abstract = {Digital libraries, particularly those designed to meet the needs of educators and students, focus their primary services on the needs of their end users [1]. In this paper, we introduce and discuss the types of services authors of the materials cataloged within this type of digital library expect, or may find useful. Results from a study of authors cataloged in NEEDS - a national engineering education digital library, guide this discussion and illustrate the challenges associated with meeting the needs of authors who are critical to the continued growth of educational digital libraries.} } @INPROCEEDINGS{Mischo02 ,AUTHOR = "William H. Mischo and Thomas G. Habing and Timothy W. Cole" ,TITLE = "Integration of Simultaneous Searching and Reference Linking across Bibliographic Resources on the Web" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544244)" ,abstract = {Libraries and information providers are actively developing customized portals and gateway software designed to integrate secondary information resources such as A & I services, online catalogs, and publishers full-text repositories. This paper reports on a project carried out at the Grainger Engineering Library at the University of Illinois at Urbana-Champaign to provide web-based asynchronous simultaneous searching of multiple secondary information resources and integrated reference linking between bibliographic resources. The project has tested two different approaches to simultaneous broadcast searching. One approach utilizes custom distributed searchbots and shared blackboard databases. The other approach uses event- driven asynchronous HTTP queries within a single web script. The reference linking implementation is built around the application of OpenURL and Digital Object Identifier (DOI) technologies and the CrossRef metadata database within a proxy server environment.} } @INPROCEEDINGS{Newman02 ,AUTHOR = " Paula S. Newman" ,TITLE = "Exploring Discussion Lists: Steps and Directions" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544245)" ,abstract = {This paper describes some new facilities for exploring archived email-based discussion lists. The facilities exploit some specific properties of email messages to obtain improved archive overviews, and then use new tree visualizations, developed for the purpose, to obtain thread overviews and mechanisms to aid in the coherent reading of threads. We consider these approaches to be limited, but useful, approximations to more ideal facilities; a final section suggests directions for further work in this area.} } @INPROCEEDINGS{Chau02 ,AUTHOR = "Michael Chau and Hsinchun Chen and Jialun Qin and Yilu Zhou and Yi Qin and Wai-Ki Sung and Daniel McDonald" ,TITLE = "Comparison of Two Approaches to Building a Vertical Search Tool: A Case in the Nanotechology Domain" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544246)" ,abstract = {As the Web has been growing exponentially, it has become increasingly difficult to search for desired information. In recent years, many domain-specific (vertical) search tools have been developed to serve the information needs of specific fields. This paper describes two approaches to building a domain-specific search tool. We report our experience in building two different tools in the nanotechnology domain -- (1) a server-side search engine, and (2) a client-side search agent. The designs of the two search systems are presented and discussed, and their strengths and weaknesses are compared. To our knowledge, this paper is the first to compare prototype vertical search systems built by the two different approaches. Some future research directions are also discussed.} } @INPROCEEDINGS{Lyu02 ,AUTHOR = "Michael R. Lyu and Edward Yau and Sam Sze" ,TITLE = "A Multilingual, Multimodal Digital Video Library System" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544248)" ,abstract = {We describe a multilingual, multimodal digital video content management system, iVIEW, for intelligent searching and access of English and Chinese video contents. The iVIEW system allows full content indexing, searching and retrieval of multilingual text, audio and video material. iVIEW integrates image processing techniques for scenes and scene changes analyses, speech processing techniques for audio signal transcriptions, and multilingual natural language processing techniques for word relevance determination. iVIEW is composed of three subsystems: Video Information Processing (VIP) Subsystem for multi-modal information processing of rich video media, Searching and Indexing Subsystem for constructing XML-based multimedia representation in enhancing multi-modal indexing and searching capabilities, and Visualization and Presentation Subsystem for flexible and seamless delivery of multimedia contents in various browsing tools and devices.} } @INPROCEEDINGS{Minibayeva02 ,AUTHOR = "Natalia Minibayeva and Jon W. Dunn" ,TITLE = "A Digital Library Data Model for Music" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544249)" ,abstract = {In this paper, we introduce a data and metadata model for music content. We discuss motivations for creation of the model, outline its basic structure, and discuss how it will be used in a music digital library system which we is presently being built.} } @INPROCEEDINGS{HauptmannA02 ,AUTHOR = "Alex Hauptmann and Norman Papernick" ,TITLE = "Video-Cuebik: Adapting Image Search to Video Shots" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544250)" ,abstract = {We propose a new analysis for searching images in video libraries that goes beyond simple image search, which compares one still image frame to another. The key idea is to expand the definition of an image to account for the variability in the sequence of video frames that comprise a shot. A first implementation of this method for a QBIC-like image search engine shows a clear improvement over still image search. A combination of the traditional still image search and the new video image search provided the overall best results on the TREC video retrieval evaluation data.} } @INPROCEEDINGS{Rowe02 ,AUTHOR = "Neil C. Rowe" ,TITLE = "Virtual Multimedia Libraries Built from the Web" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544251)" ,abstract = {We have developed a tool MARIE-4 for building virtual libraries of multimedia (images, video, and audio) by automatically exploring (crawling) a specified subdomain of the World Wide Web to create an index based on caption keywords. Our approach uses carefully-researched criteria to identify and rate caption text, and employs both an expert system and a neural network. We have used it to create a keyword-based interface to nearly all nontrivial captioned publicly-accessible U.S. Navy images (667,573), video (8,290), and audio (2,499), called the Navy Virtual Multimedia Library (NAVMULIB).} } @INPROCEEDINGS{HauptmannB02 ,AUTHOR = "Alex Hauptmann and Rong Jin and Tobun Dorbin Ng" ,TITLE = "Multi-modal Information Retrieval from Broadcast Video using OCR and Speech Recognition" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544252)" ,abstract = {We examine multi-modal information retrieval from broadcast video where text can be read on the screen through OCR and speech recognition can be performed on the audio track. OCR and speech recognition are compared on the 2001 TREC Video Retrieval evaluation corpus. Results show that OCR is more important that speech recognition for video retrieval. OCR retrieval can further improve through dictionary-based post-processing. We demonstrate how to utilize imperfect multi-modal metadata results to benefit multi-modal information retrieval.} } @INPROCEEDINGS{Ipeirotis02 ,AUTHOR = "Panagiotis G. Ipeirotis and Tom Barry and Luis Gravano" ,TITLE = "Extending SDARTS: Extracting Metadata from Web Databases and Interfacing with the Open Archives Initiative" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544254)" ,abstract = {SDARTS is a protocol and toolkit designed to facilitate metasearching. SDARTS combines two complementary existing protocols, SDLIP and STARTS, to define a uniform interface that collections should support for searching and exporting metasearch-related metadata. SDARTS also includes a toolkit with wrappers that are easily customized to make both local and remote document collections SDARTS-compliant. This paper describes two significant ways in which we have extended the SDARTS toolkit. First, we have added a tool that automatically builds rich content summaries for remote web collections by probing the collections with appropriate queries. These content summaries can then be used by a metasearcher to select over which collections to evaluate a given query. Second, we have enhanced the SDARTS toolkit so that all SDARTS-compliant collections export their metadata under the emerging Open Archives Initiative OAI) protocol. Conversely, the SDARTS toolkit now also allows all OAI-compliant collections to be made SDARTS- compliant with minimal effort. As a result, we implemented a bridge between SDARTS and OAI, which will facilitate easy interoperability among a potentially large number of collections. The SDARTS toolkit, with all related documentation and source code, is publicly available at http://sdarts.cs.columbia.edu.} } @INPROCEEDINGS{Prom02 ,AUTHOR = "Christopher J. Prom and Thomas G. Habing" ,TITLE = "Using the Open Archives Initiative Protocols with EAD" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544255)" ,abstract = {The Open Archives Initiative Protocols present a promising opportunity to make metadata about archives, manuscript collections, and cultural heritage resources easier to locate and search. However, several technical barriers must be overcome before useful OAI records can be produced from the disparate metadata formats used to describe these resources. This paper examines the case of Encoded Archival Description (EAD) as a test case of the issues to be addressed in mapping cultural heritage metadata to OAI. Encoding guidelines and selected EAD files are analyzed, and a suggested mapping from EAD to OAI is provided. The paper suggests that in some cases it may be necessary to create numerous OAI records from one source file. In addition, the findings indicate that further standardization of EAD markup practices would enhance interoperability.} } @INPROCEEDINGS{Anan02 ,AUTHOR = "H. Anan and X. Liu and K. Maly and M. Nelson and M. Zubair and J. C. French and E. Fox and P. Shivakumar" ,TITLE = "Preservation and Transition of NCSTRL Using an OAI-Based Architecture" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544256)" ,abstract = {NCSTRL (Networked Computer Science Technical Reference Library) is a federation of digital libraries providing computer science materials. The architecture of the original NCSTRL was based largely on the Dienst software. It was implemented and maintained by the digital library group at Cornell University until September 2001. At that time, we had an immediate goal of preserving the existing NCSTRL collection and a long-term goal of providing a framework where participating organizations could continue to disseminate technical publications. Moreover, we wanted the new NCSTRL to be based on OAI (Open Archives Initiative) principles that provide a framework to facilitate the discovery of content in distributed archives. In this paper, we describe our experience in moving towards an OAI-based NCSTRL.} } @INPROCEEDINGS{Smith02 ,AUTHOR = "David A. Smith and Anne Mahoney and Gregory Crane" ,TITLE = "Integrating Harvesting into Digital Library Content" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544257)" ,abstract = {The Open Archives Initiative has gained success by aiming between complex federation schemes and low functionality web crawling. Much information still remains hidden inside documents catalogued by OAI metadata. We discuss how subdocument information can be exposed by data providers and exploited by service providers. We demonstrate services for citation reversal and name and term linking with harvested data in the Perseus Project's document management system.} } @INPROCEEDINGS{Larson02 ,AUTHOR = "Ray R. Larson and Fredric Gey and Aitao Chen and Michael Buckland" ,TITLE = "Harvesting Translingual Vocabulary Mappings for Multilingual Digital Libraries" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544259)" ,abstract = {This paper presents a method of information harvesting and consolidation to support the multilingual information requirements for cross-language information retrieval within digital library systems. We describe a way to create both customized bilingual dictionaries and multilingual query mappings from a source language to many target languages. We will describe a multilingual conceptual mapping resource with broad coverage (over 100 written languages can be supported) that is truly multilingual as opposed to bilingual parings usually derived from machine translation. This resource is derived from the 10+ million title online library catalog of the University of California. It is created statistically via maximum likelihood associations from word and phrases in book titles of many languages to human assigned subject headings in English. The 150,000 subject headings can form interlingua mappings between pairs of languages or from one language to several languages. While our current demonstration prototype maps between ten languages (English, Arabic, Chinese, French, German, Italian, Japanese, Portuguese, Russian, Spanish), extensions to additional languages are straightforward. We also describe how this resource is being expanded for languages where linguistic coverage is limited in our initial database, by automatically harvesting new information from international online library catalogs using the Z39.50 networked library search protocol.} } @INPROCEEDINGS{SmithB02 ,AUTHOR = "David A. Smith" ,TITLE = "Detecting Events with Date and Place Information in Unstructured Text" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544260)" ,abstract = {Digital libraries of historical documents provide a wealth of information about past events, often in unstructured form. Once dates and place names are identified and disambiguated, using methods that can differ by genre, we examine collocations to detect events. Collocations can be ranked by several measures, which vary in effectiveness according to type of events, but the log-likelihood measure offers a reasonable balance between frequently and infrequently mentioned events and larger and smaller spatial and temporal ranges. Significant date-place collocations can be displayed on timelines and maps as an interface to digital libraries. More detailed displays can highlight key names and phrases associated with a given event.} } @INPROCEEDINGS{Soo02 ,AUTHOR = "Von-Wun Soo and Chen-Yu Lee and Chao-Chun Yeh and Ching-chih Chen" ,TITLE = "Using Sharable Ontology to Retrieve Historical Images" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544261)" ,abstract = {We present a framework of utilizing sharable domain ontology and thesaurus to help the retrieval of historical images of the First Emperor of China's terracotta warriors and horses. Incorporating the sharable domain ontology in RDF and RDF schemas of semantic web and a thesaurus, we implement methods to allow easily annotating images into RDF instances and parsing natural language like queries into the query schema in XML format. We also implement a partial structural matching algorithm to match the query schema with images at the level of semantic schemas. Therefore the historical images can be retrieved by native users of domain specific history in terms of natural language like queries.} } @INPROCEEDINGS{Kochumman02 ,AUTHOR = "Rajiv Kochumman and Carlos Monroy and Richard Furuta and Arpita Goenka and Eduardo Urbina and Erendira Melgoza" ,TITLE = "Towards an Electronic Variorum Edition of Cervantes' Don Quixote: Visualizations that Support Preparation" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544262)" ,abstract = {The Cervantes Project is creating an Electronic Variorum Edition (EVE) of Cervantes' well-known Don Quixote de la Mancha, published beginning in 1605. In this paper, we report on visualizations of features of a text collection that help us validate our text transcriptions and understand the relationships among the different printings of an edition.} } @INPROCEEDINGS{Lagoze02 ,AUTHOR = "Carl Lagoze and Walter Hoehn and David Millman and William Arms and Stoney Gan and Diane Hillmann and Christopher Ingram and Dean Krafft and Richard Marisa and Jon Phipps and John Saylor and Carol Terrizzi and James Allen and Sergio Guzman-Lara and Tom Kalt" ,TITLE = "Core Services in the Architecture of the National Digital Library for Science Education" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544264)" ,abstract = {We describe the core components of the architecture for the (NSDL) National Science, Mathematics, Engineering, and Technology Education Digital Library. Over time the NSDL will include heterogeneous users, content, and services. To accommodate this, a design for a technical and organization infrastructure has been formulated based on the notion of a spectrum of interoperability. This paper describes the first phase of the interoperability infrastructure including the metadata repository, search and discovery services, rights management services, and user interface portal facilities.} } @INPROCEEDINGS{Geisler02 ,AUTHOR = "Gary Geisler and Sarah Giersch and David McArthur and Marty McClelland" ,TITLE = "Creating Virtual Collections in Digital Libraries: Benefits and Implementation Issues" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544265)" ,abstract = {Digital libraries have the potential to not only duplicate many of the services provided by traditional libraries but to extend them. Basic finding aids such as search and browse are common in most of today's digital libraries. But just as a traditional library provides more than a card catalog and browseable shelves of books, an effective digital library should offer a wider range of services. Using the traditional library concept of special collections as a model, in this paper we propose that explicitly defining sub-collections in the digital library-virtual collections-can benefit both the library's users and contributors and increase its viability. We first introduce the concept of a virtual collection, outline the costs and benefits for defining such collections, and describe an implementation of collection- level metadata to create virtual collections for two different digital libraries. We conclude by discussing the implications of virtual collections for enhancing interoperability and sharing across digital libraries, such as those that are part of the National SMETE Digital Library.} } @INPROCEEDINGS{Gupta02 ,AUTHOR = "Amarnath Gupta and Bertram Ludaescher and Reagan W. Moore" ,TITLE = "Ontology Services for Curriculum Development in NSDL" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544266)" ,abstract = {We describe our effort to develop an ontology service on top of an educational digital library. The ontology is developed by relating library holdings to the educational concepts they refer to. The ontology system supports basic services like ontology-based search and complex services such as comparison of multiple curricula.} } @INPROCEEDINGS{Kassim02 ,AUTHOR = "Ahmad Rafee Che Kassim and Thomas R. Kochtanek" ,TITLE = "Interactive Digital Library Resource Information System: A Web Portal for Digital Library Education" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544267)" ,abstract = {This paper describes a collaborative database project that focuses on access to materials on topics relating to digital libraries that are organized within an educational framework. } } @INPROCEEDINGS{Dunker02 ,AUTHOR = "Elke Dunker" ,TITLE = "Cross-cultural Usability of the Library Metaphor" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544269)" ,abstract = {Computing metaphors have become an intricate part of information systems design. Yet, they are deeply rooted in cultural practices. This paper presents an investigation of the cross-cultural use and usability of the library metaphor in digital libraries. The study examines the relevant features of the Maori culture in New Zealand, their form of knowledge transfer and their use of real world and digital libraries. On this basis the paper points out why and when the library metaphor fails Maori and other indigenous users and how this knowledge can contribute to the improvement of future designs.} } @INPROCEEDINGS{House02 ,AUTHOR = "Nancy Van House" ,TITLE = "Trust and Epistemic Communities in Biodiversity Data Sharing" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544270)" ,abstract = {All knowledge work is, in some sense, collaborative. Trust is a key element of knowledge work: what we know depends largely on others. A better understanding of the epistemic machineries of knowledge communities and especially their practices of trust would be useful for designing effective digital libraries. This paper discusses the concepts of communities of practice and epistemic cultures, and their implication for design of digital libraries that support data sharing, with particular reference to practices of trust and credibility. It uses an empirical study of a biodiversity data system that collects and distributes data from a variety of sources to illustrate the implications of these concepts of knowledge communities for digital library design and operation. It concludes that diversity and uncomfortable boundary areas typify, not only digital library user groups, but the design and operation of digital libraries.} } @INPROCEEDINGS{Unruh02 ,AUTHOR = "K.T. Unruh and K.E. Pettigrew and J.C. Durrance" ,TITLE = "Evaluation of Digital Community Information Systems" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544271)" ,abstract = {Community information systems provide a critical link between local resources and residents. While online versions of these systems have potential benefits, a systematic evaluation framework is needed to analyze and document realized impacts. Based on data from a nation-wide study of digital community information systems, an evaluation framework is proposed.} } @INPROCEEDINGS{Barkstrom02 ,AUTHOR = "Bruce R. Barkstrom and Melinda Finch and Michelle Ferebee and Calvin Mackey" ,TITLE = "Adapting Digital Libraries to Continual Evolution" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544272)" ,abstract = {In this paper, we describe five investment streams (data storage infrastructure, knowledge management, data production control, data transport and security, and personnel skill mix) that need to be balanced against short-term operating demands in order to maximize the probability of long-term viability of a digital library. Because of the rapid pace of information technology change, a digital library cannot be a static institution. Rather, it has to become a flexible organization adapted to continuous evolution of its infrastructure.} } @INPROCEEDINGS{Dushay02 ,AUTHOR = "Naomi Dushay" ,TITLE = "Localizing Experience of Digital Content via Structural Metadata" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,lnks = "(title:www:http://doi.acm.org/10.1145/544220.544274)" ,abstract = {With the increasing technical sophistication of both information consumers and providers, there is increasing demand for more meaningful experiences of digital information. We present a framework that separates digital object experience, or rendering, from digital object storage and manipulation, so the rendering can be tailored to particular communities of users. Our framework also accommodates extensible digital object behaviors and interoperability. The two key components of our approach are 1) exposing structural metadata associated with digital objects - metadata about labeled access points within a digital object and 2) information intermediaries called context brokers that match structural characteristics of digital objects with mechanisms that produce behaviors. These context brokers allow for localized rendering of digital information stored externally.} } @INPROCEEDINGS{Bergmark02 ,AUTHOR = "Donna Bergmark" ,TITLE = "Collection Synthesis" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544275)" ,abstract = {The invention of the hyperlink and the HTTP transmission protocol caused an amazing new structure to appear on the Internet -- the World Wide Web. With the Web, there came spiders, robots, and Web crawlers, which go from one link to the next checking Web health, ferreting out information and resources, and imposing organization on the huge collection of information (and dross) residing on the net. This paper reports on the use of one such crawler to synthesize document collections on various topics in science, mathematics, engineering and technology. Such collections could be part of a digital library.} } @INPROCEEDINGS{Goncalves02 ,AUTHOR = "Marcos Andre Goncalves and Edward A. Fox" ,TITLE = "5SL -- A Language for Declarative Specification and Generation of Digital Libraries" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544276)" ,abstract = {Digital libraries (DLs) are among the most complex kinds of information systems, due in part to their intrinsic multi-disciplinary nature. Nowadays DLs are built within monolithic, tightly integrated, and generally inflexible systems -- or by assembling disparate components together in an ad-hoc way, with resulting problems in interoperability and adaptability. More importantly, conceptual modeling, requirements analysis, and software engineering approaches are rarely supported, making it extremely difficult to tailor DL content and behavior to the interests, needs, and preferences of particular communities. In this paper, we address these problems. In particular, we present 5SL, a declarative language for specifying and generating domain- specific digital libraries. 5SL is based on the 5S formal theory for digital libraries and enables high-level specification of DLs in five complementary dimensions, including: the kinds of multimedia information the DL supports (Stream Model); how that information is structured and organized (Structural Model); different logical and presentational properties and operations of DL components (Spatial Model); the behavior of the DL (Scenario Model); and the different societies of actors and managers of services that act together to carry out the DL behavior (Societal Model). The practical feasibility of the approach is demonstrated by the presentation of a 5SL digital library generator for the MARIAN digital library system.} } @INPROCEEDINGS{Dunlop02 ,AUTHOR = "Hayley Dunlop and Matt Jones and Sally Jo Cunningham" ,TITLE = "A Digital Library of Conversational Expressions: A Communication Aid for People with Profound Physical Disabilities" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544278)" ,abstract = {This paper describes the development of a communication aid for people with profound physical disabilities, people who cannot communicate verbally, and who cannot use conventional communication tools. The Greenstone digital library software has been used to construct a digital library of common conversational expressions. A case study approach was adopted, and the target user for this particular digital library was a local high school student. Tailoring the digital library's contents to this user entailed identifying physical accessibility considerations for her, developing a suitable mode of interaction with the digital library software, populating the digital library with appropriate expressions for her, and evaluating the digital library interface. Evaluation involved both a qualitative user evaluation session and a quantitative analysis of the time and effort required to use each of three proposed searching interfaces.} } @INPROCEEDINGS{Wang02 ,AUTHOR = "Jun Wang and Abhishek Agrawal and Anil Bazaz and Supriya Angle and Edward A. Fox and Chris North" ,TITLE = "Enhancing the ENVISION Interface for Digital Libraries" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544279)" ,abstract = {To enhance the ENVISION interface and facilitate user interaction, various techniques were considered for better rendering of search results with improved scalability. In this paper we discuss the challenges we encountered and our solutions to those problems.

The Envision interface helps visualize search results from the MARIAN digital library system. The old Envision interface featured a Query Screen, Result Visualization Screen, and Result List Screen. Envision presented each document in the result set graphically as an icon. The user could select several documents on the Visualization Screen and see corresponding details in the Result List Screen. Envision used a rigid matrix to display search results. As with various other visualization tools, it provided no overview, thus no context information to users. Scrollbars were needed for data outside the viewable area. In working to enhance Envision, we considered other efforts. Some approaches (e.g., ThemeScapes) are almost exactly opposite, displaying data in a completely flexible manner. The data is not bound to any axis but is arranged according to relationships between documents. We now explore a middle ground with an overview as well as loose matrix arrangement, with related documents mapped together.} } @INPROCEEDINGS{Lin02 ,AUTHOR = "Wei-hao Lin and Alex Hauptmann" ,TITLE = "A Wearable Digital Library of Personal Conversations" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544280)" ,abstract = {We have developed a wearable, personalized digital library system, which unobtrusively records the wearer's part of a conversation, recognizes the face of the current dialog partner and remembers his/her voice. The next time the system sees the same person's face and hears the same voice, it can replay the audio from the last conversation in compressed form summarizing the names and major issues mentioned. Experiments with a prototype system show that a combination of face recognition and speaker identification can be effective for retrieving conversations.} } @INPROCEEDINGS{Borner02 ,AUTHOR = "Katy Borner and Ying Feng and Tamara McMahon" ,TITLE = "Collaborative Visual Interfaces to Digital Libraries" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544281)" ,abstract = {This paper argues for the design of collaborative visual interfaces to digital libraries that support social navigation. As an illustrative example we present work in progress on the design of a three-dimensional document space for a scholarly community - namely faculty, staff, and students at the School of Library and Information Science, Indiana University. We conclude with a set of research challenges.} } @INPROCEEDINGS{Cubaud02 ,AUTHOR = "Pierre Cubaud and Pascal Stokowski and Alexandre Topol" ,TITLE = "Binding Browsing and Reading Activities in a 3D Digital Library" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544282)" ,abstract = {Browsing through collections and reading activities are separated in most present WWW-based user's interfaces of digitalized libraries. This context break induces longer apprenticeship and navigation time within the interface. We study in this paper how 3D interaction metaphors can be used to provide a continuous navigation space for these two tasks.} } @INPROCEEDINGS{LiuX02 ,AUTHOR = "Xiaoming Liu and Kurt Maly and Mohammad Zubair and Michael L. Nelson" ,TITLE = "DP9- An OAI Gateway Service for Web Crawlers" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544284)" ,abstract = {Many libraries and databases are closed to general-purpose web crawlers, and they expose their content only to their own search engines. At the same time many use general-purpose search engines to locate research papers. DP9 is an open source gateway service that allows general search engines, (e.g. Google, Inktomi) to index OAI-compliant archives. DP9 does this by providing consistent URLs for repository records, and converting them to OAI queries against the appropriate repository when the URL is requested. This allows search engines that do not support the OAI protocol to index the "deep web" contained within OAI compliant repositories.} } @INPROCEEDINGS{Witten02 ,AUTHOR = " Ian H. Witten and David Bainbridge and Gordon Paynter and Stefan Boddie" ,TITLE = "The Greenstone Plugin Architecture" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544285)" ,abstract = {Flexible digital library systems need to be able to accept documents and metadata in a variety of forms. This paper describes an architecture based on plugins that allows one to import documents and metadata in different formats, and associate metadata with the appropriate documents. Plugins that import documents can perform their own format conversion internally, or take advantage of existing conversion programs. Metadata can be read from the input documents, or from separate metadata files, or can in some cases be computed from the documents themselves. It is easy to write new plugins for novel situations.} } @INPROCEEDINGS{Gold02 ,AUTHOR = "Anna Keller Gold and Karen Baker and Kim Baldridge and Jean-Yves Le Meur" ,TITLE = "Building FLOW: Federating Libraries on the Web" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544286)" ,abstract = {An individual scientist, a collaborative team and a research network have a variety of document management needs in common. The levels of research organization, when viewed as nested tiers, represent boundaries across which information can flow openly if technology and metadata standards are partnered to provide an accessible, interoperable digital framework. The CERN Document System (CDS), implemented by a research partnership at the San Diego Supercomputer Center (SDSC), establishes a prototype tiered repository system. An ongoing exploration of existing scientific research information infrastructure suggests modifications to enable cross-tier and cross-domain information flow across what could be represented as a metadata grid.} } @INPROCEEDINGS{Corfield02 ,AUTHOR = "Antony Corfield and Matthew Dovey and Richard Mawby and Colin Tatham" ,TITLE = "JAFER ToolKit Project - Interfacing Z39.50 and XML" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544287)" ,abstract = {In this paper, we describe the JAFER ToolKit project which is developing a simplified XML based API above the Z39.50 protocol. The ToolKit allows the development of both Z39.50 based applications (both clients and servers) without detailed knowledge of the complexities of the protocol.} } @INPROCEEDINGS{Childovskii02 ,AUTHOR = "Boris Childovskii" ,TITLE = "Schema Extraction from XML Collections" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544288)" ,abstract = {XML Schema language has been proposed to replace Document Type Definitions (DTDs) as schema mechanism for XML data. This language consistently extends grammar-based constructions with constraint- and pattern-based ones and have a higher expressive power than DTDs. As schemas remain optional for XML, we address the problem of XML Schema extraction. We model the XML schema as extended context-free grammars and develop a novel extraction algorithm inspired by methods of grammatical inference. The algorithm copes also with the schema determinism requirement imposed by XML DTDs and XML Schema languages.} } @INPROCEEDINGS{Pande02 ,AUTHOR = "Ashwini Pande and Malini Kothapalli and Ryan Richardson and Edward A. Fox" ,TITLE = "Mirroring an OAI Archive on the I2-DSI Channel" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544289)" ,abstract = {The Open Archives Initiative (OAI) promotes interoperability among digital libraries and has created a protocol for data providers to easily export their metadata. One problem with this approach is that some of the more popular servers quickly become heavily loaded. The obvious solution is replication. Fortunately, the Internet-2 Distributed Storage Infrastructure (I2-DSI) has begun to develop technology for highly distributed transparent replication of servers. This paper presents our solution for transparent mirroring of OAI repositories within the I2-DSI.} } @INPROCEEDINGS{Shifrin02 ,AUTHOR = "Jonah Shifrin and Bryan Pardo and Colin Meek and William Birmingham" ,TITLE = "HMM-Based Musical Query Retrieval" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544291)" ,abstract = {We have created a system for music search and retrieval. A user sings a theme from the desired piece of music. Pieces in the database are represented as hidden Markov models (HMMs). The query is treated as an observation sequence and a piece is judged similar to the query if its HMM has a high likelihood of generating the query. The top pieces are returned to the user in rank-order. This paper reports the basic approach for the construction of the target database of themes, encoding and transcription of user queries, and the results of initial experimentation with a small set of sung queries.} } @INPROCEEDINGS{Hu02 ,AUTHOR = "Ning Hu and Roger B. Dannenberg" ,TITLE = "A Comparison of Melodic Database Retrieval Techniques Using Sung Queries" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links ="(title:www:http://doi.acm.org/10.1145/544220.544292)" ,abstract = {Query-by-humming systems search a database of music for good matches to a sung, hummed, or whistled melody. Errors in transcription and variations in pitch and tempo can cause substantial mismatch between queries and targets. Thus, algorithms for measuring melodic similarity in query-by- humming systems should be robust. We compare several variations of search algorithms in an effort to improve search precision. In particular, we describe a new frame-based algorithm that significantly outperforms note-by-note algorithms in tests using sung queries and a database of MIDI-encoded music. Keywords dynamic programming, melodic comparison, melodic searching, Music Information Retrieval (MIR), sung query} } @INPROCEEDINGS{Wingenroth02 ,AUTHOR = "Brian Wingenroth and Mark Patton and Tim DiLauro" ,TITLE = "Enhancing Access to the Levy Sheet Music Collection: Reconstructing Full-Text Lyrics from Syllables" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544293)" ,abstract = {The goal of the Lester S. Levy Sheet Music Collection, Phase Two project is to develop tools, processes, and systems that facilitate collection ingestion through automated processes that reduce, but not necessarily eliminate human intervention. One of the major components of this project is an optical music recognition (OMR) system that extracts musical information and lyric text from the page images that comprise each piece in a collection. It is often the case, as it is with the Levy Collection, that lyrics embedded in music notation are written in a syllabicated form so that each syllable lines up with the note or notes to which it corresponds. Searching the syllabicated form of words, however, would be counterintuitive and cumbersome for end-users. This paper describes a tool that, using a simple algorithm, rebuilds complete words from lyric syllables and, in ambiguous cases, provides feedback to the collection builder. This system will be integrated into the workflow of the Levy Sheet Music Collection, but has broad applicability for any project ingesting musical scores with lyrics.} } @INPROCEEDINGS{Melucci02 ,AUTHOR = " Massimo Melucci and Nicola Orio" ,TITLE = "Evaluating Automatic Melody Segmentation Aimed at Music Information Retrieval" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544294)" ,abstract = {The main contribution of this paper is an investigation on the effects of exploiting melodic features for automatic melody segmentation aimed at content-based music retrieval. We argue that segmentation based on melodic features is more effective than random or n-grams-based segmentation, which ignore any context. We have carried out an experiment employing experienced subjects. The manual segmentation result has been processed to detect the most probable boundaries in the melodic surface, using a probabilistic decision function. The detected boundaries have then been compared with the boundaries detected by an automatic procedure implementing an algorithm for melody segmentation, as well as by a random segmenter and by a n-gram-based segmenter. Results showed that automatic segmentation based on melodic features is closer to manual segmentation than algorithms that do not use such information.} } @INPROCEEDINGS{Lorie02 ,AUTHOR = "Raymond A. Lorie" ,TITLE = "A Methodology and System for Preserving Digital Data" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544296)" ,abstract = {This paper refers to a previous proposal made at the 1st Joint Conference on Digital Libraries, on a novel approach to the problem of the long-term archival of digital data. It reports on ongoing work in refining the methodology and building an initial prototype. The method is based on the use of a Universal Virtual Computer (UVC) to specify the process that needs to be applied to the archived data in order to make it understandable for a future client. There is a certain amount of information (a Convention) that must be preserved for an indefinite time, to make sure that the client will be able to recover the information. A first version of this Convention is given here; it includes the architecture of the UVC. The paper also briefly mentions our current activities in implementation and evaluation.} } @INPROCEEDINGS{French02 ,AUTHOR = "James C. French" ,TITLE = "Modeling Web Data" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544297)" ,abstract = {We have created three testbeds of web data for use in controlled experiments in collection modeling. This short paper examines the applicability of Ziff's and Heaps' laws as applied to web data. We find extremely close agreement between observed vocabulary growth and Heaps' law. We find reasonable agreement with Ziff's law for medium to low frequency terms. Ziff's law is a poor predictor for high frequency terms. These findings hold for all three testbeds although we restrict ourselves to one here due to space limitations.} } @INPROCEEDINGS{Dorward02 ,AUTHOR = "Jim Dorward and Derek Reinke and Mimi Recker" ,TITLE = "An Evaluation Model for a Digital Library Services Tool" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544298)" ,abstract = {This paper describes an evaluation model for a digital library tool, the Instructional Architect, which enables users to discover, select, reuse, sequence, and annotate digital library learning objects. By documenting our rapid-prototyping, iterative, and user-centered approach for evaluating a digital library service, we provide a model and set of methods that other developers may wish to employ. In addition, we provide preliminary results from our studies.} } @INPROCEEDINGS{Seadle02 ,AUTHOR = "Michael Seadle and J. R. Deller and Aparna Gurijala" ,TITLE = "Why Watermark? The Copyright Need for an Engineering Solution" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544299)" ,abstract = {An important research component in the creation of the National Gallery of the Spoken Word (NGSW) is the development of watermarking technologies for the audio library. In this paper we argue that audio watermarking is a particularly desirable means of intellectual property protection. There is evidence that the courts consider watermarks to be a legitimate form of copyright protection. Watermarking facilitates redress, and represents a form of copyright protection that universities can use without being inconsistent in their mission to disseminate knowledge.} } @INPROCEEDINGS{Graham02 ,AUTHOR = "Adrian Graham and Hector Garcia-Molina and Andreas Paepcke and Terry Winograd" ,TITLE = "Time as Essence for Photo Browsing Through Personal Digital Libraries" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2002-4)" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544301)" ,entered-by = "Rebecca Wesley" ,abstract = {We developed two photo browsers for collections with thousands of time-stamped digital images. Modern digital cameras record photo shoot times, and semantically related photos tend to occur in bursts. Our browsers exploit the timing information to structure the collections and to automatically generate meaningful summaries. The browsers differ in how users navigate and view the structured collections. We conducted user studies to compare the two browsers and a commercial image browser. Our results show that exploiting the time dimension and appropriately summarizing collections can lead to significant improvements. For example, for one task category, one of our browsers enabled a 33% improvement in speed of finding given images compared to the commercial browser. Similarly, users were able to complete 29% more tasks when using this same browser.} } @INPROCEEDINGS{LiuB02 ,AUTHOR = "Bin Liu and Wen Gao and Tie-jun Huang and Ling Zhang and Jun Che" ,TITLE = "Toward a Distributed Terabyte Text Retrieval System in China-US Million Book Digital Library" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544302)" ,abstract = {In China-US Million Book Digital Library, output of the digitalization process is more than one terabyte of text in OEB and PDF format. To access these data quickly and accurately, we are developing a distributed terabyte text retrieval system. With the query cache, system can search less data while maintaining acceptable retrieval accuracy. From the OEB package, we get its metadata and structural information to implement multi-scale indexing and retrieval. We are to explore some new ranking and relevance feedback approaches.} } @INPROCEEDINGS{Wactlar02 ,AUTHOR = "Howard D. Wactlar and Ching-chih Chen" ,TITLE = "Enhanced Perspectives for Historical and Cultural Documentaries Using Informedia Technologies" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544303)" ,abstract = {Speech recognition, image processing, and language understanding technologies have successfully been applied to broadcast news corpora to automate the extraction of metadata and make use of it in building effective video news retrieval interfaces. This paper discusses how these technologies can be adapted to cultural documentaries as represented by the award-winning First Emperor of China videodisc and multimedia CD. Through automated means, efficient interfaces into documentary contents can be built dynamically based on user needs. Such interfaces enable the assemblage of large video documentary libraries from component videodisc, CD, and videotape projects, with alternate views into the material complementing the original sequences authored by the materials' producers.} } @INPROCEEDINGS{Derthick02 ,AUTHOR = "Mark Derthick" ,TITLE = "Interfaces for Palmtop Image Search" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544304)" ,abstract = {We expect that people will want to search for video news or entertainment on mobile platforms as soon as the technology is ready. An Ipaq palmtop version of the Informedia Digital Video Library interface has already been developed at the Chinese University of Hong Kong. Separately, we used the Desktop Informedia interface for the interactive part of the Trec10 video track competition. The lesson we learned is that automated image search is so poor that the best interactive results come from showing the user many images quickly, and allowing flexible drill down to images from nearby shots. Here we report on an effort to apply this lesson to palmtop platforms, where showing a large grid of images in parallel is not feasible. Perceptual psychology experiments suggest that time-multiplexing may be as effective as space-multiplexing for this kind of primed recognition task. In fact, it has been specifically suggested that image retrieval interfaces using Rapid Serial Visual Presentation (RSVP) may perform significantly better than parallel presentation even on a desktop computer [2]. In our experiments, we did not find this to be true. An important difference between previous experiments and our own, we discovered, is that image search engines rank retrievals, and correct answers are more likely to occur early in the list of results. Thus we found that scrolling (and low RSVP presentation rates) led to better recognition of answers that occur early, but worse for answers that occur far down the list. This split confounded the global effects that we had hypothesized, yet in itself is an important consideration for future interface designs, which must adapt as search technology improves.} } @INPROCEEDINGS{Janee02 ,AUTHOR = "Greg Janée and James Frew" ,TITLE = "The ADEPT Digital Library Architecture" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544306)" ,abstract = {The Alexandria Digital Earth ProtoType (ADEPT) architecture is a framework for building distributed digital libraries of georeferenced information. An ADEPT system comprises of one or more autonomous libraries, each of which provides a uniform interface to one or more collections, each of which manages metadata for one or more items. The primary standard on which the architecture is based is the ADEPT bucket framework, which defines uniform client-level metadata query services that are compatible with heterogeneous underlying collections. ADEPT functionality strikes a balance between the simplicity of Web document delivery and the richness of Z39.50. The current ADEPT implementation runs as servlet-based middleware and supports collections housed in arbitrary relational databases.} } @INPROCEEDINGS{LimE02 ,AUTHOR = "Ee-Peng Lim and Dion Hoe-Lian Goh and Zehua Liu and Wee-Keong Ng and Christopher Soo-Guan Khoo and Susan Ellen Higgins" ,TITLE = "G-Portal: A Map-based Digital Library for Distributed Geospatial and Georeferenced Resources" ,BOOKTITLE = jcdl02 ,YEAR = "2002" ,entered-by = "Rebecca Wesley" ,links = "(title:www:http://doi.acm.org/10.1145/544220.544307)" ,abstract = {As the World Wide Web evolves into an immense information network, it is tempting to build new digital library services and expand existing digital library services to make use of web content. In this paper, we present the design and implementation of G-Portal, a web portal that aims to provide digital library services over geospatial and georeferenced content found on the World Wide Web. G-Portal adopts a map-based user interface to visualize and manipulate the distributed geospatial and georeferenced content. Annotation capabilities are supported, allowing users to contribute geospatial and georeferenced objects as well as their associated metadata. The other features included in G-Portal's design are query support, content classification, and content maintenance. This paper will mainly focus on the architecture design, visualization and annotation capabilities of G-Portal.} } @TECHREPORT{Yangb01 ,AUTHOR = "Beverly Yang and Hector Garcia-Molina" ,TITLE = "Comparing Hybrid Peer-to-Peer Systems (25 page)" ,INSTITUTION = "Stanford University" ,YEAR = "2001" ,number = "2001-37" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2001-37)" ,entered-by = "Rebecca Wesley" ,abstract = { "Peer-to-peer" systems like Napster and Gnutella have recently become popular for sharing information. In this paper, we study the relevant issues and tradeoffs in designing a scalable P2P system. We focus on a subset of P2P systems, known as "hybrid" P2P, where some functionality is still centralized. (In Napster, for example, indexing is centralized, and file exchange is distributed.) We model a file-sharing application, developing a probabilistic model to describe query behavior and expected query result sizes. We also develop an analytic model to describe system performance. Using experimental data collected from a running, publicly available hybrid P2P system, we validate both models. We then present several hybrid P2P system architectures and evaluate them using our model. We discuss the tradeoffs between the architectures and highlight the effects of key parameter values on system performance.} } @INPROCEEDINGS{Yangc02 ,AUTHOR = "Beverly Yang and Hector Garcia-Molina" ,TITLE = "Comparing Hybrid Peer-to-Peer Systems " ,BOOKTITLE = vldb01 ,YEAR = "2001" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2001-36)" ,entered-by = "Rebecca Wesley" ,abstract = { "Peer-to-peer" systems like Napster and Gnutella have recently become popular for sharing information. In this paper, we study the relevant issues and tradeoffs in designing a scalable P2P system. We focus on a subset of P2P systems, known as "hybrid" P2P, where some functionality is still centralized. (In Napster, for example, indexing is centralized, and file exchange is distributed.) We model a file-sharing application, developing a probabilistic model to describe query behavior and expected query result sizes. We also develop an analytic model to describe system performance. Using experimental data collected from a running, publicly available hybrid P2P system, we validate both models. We then present several hybrid P2P system architectures and evaluate them using our model. We discuss the tradeoffs between the architectures and highlight the effects of key parameter values on system performance.} } @TECHREPORT{Yangd01 ,AUTHOR = "Beverly Yang and Hector Garcia-Molina" ,TITLE = "Comparing Hybrid Peer-to-Peer Systems (extended)" ,INSTITUTION = "Stanford University" ,YEAR = "2001" ,number = "2001-35" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2001-35)" ,entered-by = "Rebecca Wesley" ,abstract = { "Peer-to-peer" systems like Napster and Gnutella have recently become popular for sharing information. In this paper, we study the relevant issues and tradeoffs in designing a scalable P2P system. We focus on a subset of P2P systems, known as "hybrid" P2P, where some functionality is still centralized. (In Napster, for example, indexing is centralized, and file exchange is distributed.) We model a file-sharing application, developing a probabilistic model to describe query behavior and expected query result sizes. We also develop an analytic model to describe system performance. Using experimental data collected from a running, publicly available hybrid P2P system, we validate both models. We then present several hybrid P2P system architectures and evaluate them using our model. We discuss the tradeoffs between the architectures and highlight the effects of key parameter values on system performance.} } @INPROCEEDINGS{Daswani03 ,AUTHOR = "Neil Daswani and Hector Garcia-Molina and Beverly Yang" ,TITLE = "Open Problems in Data-sharing Peer-to-peer Systems" ,BOOKTITLE = icdt03 ,YEAR = "2003" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2003-01)" ,entered-by = "Rebecca Wesley" ,abstract = { In a Peer-To-Peer (P2P) system, autonomous computers pool their resources (e.g., files, storage, compute cycles) in order to inexpensively handle tasks that would normally require large costly servers. The scale of these systems, their "open nature," and the lack of centralized control pose difficult performance and security challenges. Much research has recently focused on tackling some of these challenges; in this paper, we propose future directions for research in P2P systems, and highlight problems that have not yet been studied in great depth. We focus on two particular aspects of P2P systems -- search and security -- and suggest several open and important research problems for the community to address.} } @TECHREPORT{Crespoa01 ,AUTHOR = "Arturo Crespo and Hector Garcia-Molina" ,TITLE = "Routing Indices For Peer-to-Peer Systems" ,INSTITUTION = "Stanford University" ,YEAR = "2001" ,number = "2001-48" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2001-48)" ,entered-by = "Rebecca Wesley" ,abstract = { Finding information in a peer-to-peer system currently requires either a costly and vulnerable central index, or flooding the network with queries. In this paper we introduce the concept of Routing Indices (RIs), which allow nodes to forward queries to neighbors that are more likely to have answers. If a node cannot answer a query, it forwards the query to a subset of its neighbors, based on its local RI, rather than by selecting neighbors at random or by flooding the network by forwarding the query to all neighbors. We present three RI schemes: the compound, the hop-count, and the exponential routing indices. We evaluate their performance via simulations, and find that RIs can improve performance by one or two orders of magnitude vs. a flooding-based system, and by up to 100% vs. a random forwarding system. We also discuss the tradeoffs between the different RI schemes and highlight the effects of key design variables on system performance.} } @TECHREPORT{Yange01 ,AUTHOR = "Beverly Yang and Hector Garcia-Molina" ,TITLE = "Improving Search in Peer-to-Peer Systems" ,INSTITUTION = "Stanford University" ,YEAR = "2001" ,number = "2001-47" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2001-47)" ,entered-by = "Rebecca Wesley" ,abstract = { Peer-to-peer systems have emerged as a popular way to share huge volumes of data. The usability of these systems depends on effective techniques to find and retrieve data; however, current techniques used in existing P2P systems are often very inefficient. In this paper, we present three techniques for efficient search in P2P systems. We present the design of these techniques, and then evaluate them using a combination of experiments over Gnutella, the largest open P2P system in operation, and analysis. We show that while our techniques maintain the same quality of results as currently used techniques, our techniques use up to 5 times fewer resources. In addition, we designed our techniques to be simple in design and implementation, so that they can be easily incorporated into existing systems for immediate impact.} } @TECHREPORT{Yangf02 ,AUTHOR = "Beverly Yang and Hector Garcia-Molina" ,TITLE = "Improving Search in Peer-to-Peer Systems" ,INSTITUTION = "Stanford University" ,YEAR = "2002" ,number = "2002-28" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2002-28)" ,entered-by = "Rebecca Wesley" ,abstract = { Peer-to-peer systems have emerged as a popular way to share huge volumes of data. The usability of these systems depends on effective techniques to find and retrieve data; however, current techniques used in existing P2P systems are often very inefficient. In this paper, we present three techniques for efficient search in P2P systems. We present the design of these techniques, and then evaluate them using a combination of analysis and experiments over Gnutella, the largest open P2P system in operation. We show that while our techniques maintain the same quality of results as currently used techniques, they use up to 5 times fewer resources. In addition, we designed our techniques to be simple, so that they can be easily incorporated into existing systems for immediate impact.} } @TECHREPORT{Deshpande02 ,AUTHOR = "Hrishikesh Deshpande and Mayank Bawa and Hector Garcia-Molina" ,TITLE = "Streaming Live Media over Peers" ,INSTITUTION = "Stanford University" ,YEAR = "2002" ,number = "2002-21" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2002-21)" ,entered-by = "Rebecca Wesley" ,abstract = { The high bandwidth required by live streaming video greatly limits the number of clients that can be served by a source using unicast. An efficient solution is IP-multicast, but it suffers from poor deployment. Application-level multicast is being increasingly recognized as a viable alternative. In this work, we discuss and evaluate a tree-based overlay network called {\em PeerCast} that uses clients to forward the stream to their peers. PeerCast is designed as a live-media streaming solution for peer-to-peer systems that are populated by hundreds of autonomous, short-lived nodes. Further, we argue for the need to take end-host behavior into account while evaluating an application-level multicast architecture. An end-host behavior model is proposed that allows us to capture a range of realistic peer behavior. Using this model, we develop robust, yet simple, tree-maintenance policies. Through empirical runs and extensive simulations, we show that PeerCast provides good QoS, which gracefully degrades with the number of clients. We have implemented a PeerCast prototype, which is available for download.} } @TECHREPORT{Cooperb02 ,AUTHOR = "Brian F. Cooper and Hector Garcia-Molina" ,TITLE = "Modeling and measuring scalable peer-to-peer search networks" ,INSTITUTION = "Stanford University" ,YEAR = "2002" ,number = "2002-44" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2002-44)" ,entered-by = "Rebecca Wesley" ,abstract = {The popularity of peer-to-peer search networks grows, even as the limitations to the scalability of existing systems become apparent. We propose a simple model for search networks, called the search/index links (SIL) model. The SIL model describes existing networks while also yielding organizations not previously studied. Using simulation results, we argue that a new organization, parallel search clusters, is superior to existing supernode networks in many cases.} } @TECHREPORT{Cooperc02 ,AUTHOR = "Brian F. Cooper and Hector Garcia-Molina" ,TITLE = "Modeling and measuring scalable peer-to-peer search networks (Extended version)" ,INSTITUTION = "Stanford University" ,YEAR = "2002" ,number = "2002-43" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2002-43)" ,entered-by = "Rebecca Wesley" ,abstract = {The popularity of peer-to-peer search networks grows, even as the limitations to scalability of existing systems becomes apparent. We propose a simple model for search networks, called the search/index links (SIL) model. The SIL model describes existing networks while also yielding organizations not previously studied. Using simulation results, we argue that a new organization, parallel search clusters, is superior to existing supernode networks in many cases.} } @TECHREPORT{Cooperd02 ,AUTHOR = "Brian Cooper and Mayank Bawa and Neil Daswani and Hector Garcia-Molina" ,TITLE = "Protecting the PIPE from malicious peers" ,INSTITUTION = "Stanford University" ,YEAR = "2002" ,number = "2002-97" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2002-97)" ,entered-by = "Rebecca Wesley" ,abstract = {Digital materials can be protected from failures by replicating them at multiple autonomous, distributed sites. A significant challenge in such a distributed system is ensuring that documents are replicated and accessible despite malicious sites. Such sites may hinder the replication of documents in a variety of ways, including agreeing to store a copy but erasing it instead, refusing to serve a document, or serving an altered version of the document. We describe the design of a a Peer-to-peer Information Preservation and Exchange (PIPE) network: a distributed replication system that protects documents both from failures and from malicious nodes. We present the design of a PIPE system, discuss a threat model for malicious sites, and propose basic solutions for managing these malicious sites.} } @TECHREPORT{Coopere02 ,AUTHOR = "Brian Cooper and Mayank Bawa and Neil Daswani and Hector Garcia-Molina" ,TITLE = "Protecting the PIPE from malicious peers" ,INSTITUTION = "Stanford University" ,YEAR = "2002" ,number = "2002-03" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2002-03)" ,entered-by = "Rebecca Wesley" ,abstract = {Digital materials can be protected from failures by replicating them at multiple autonomous, distributed sites. A Peer-to-peer Information Preservation and Exchange (PIPE) network is a good way to build a distributed replication system. A significant challenge in such networks is ensuring that documents are replicated and accessible despite malicious sites. Such sites may hinder the replication of documents in a variety of ways, including agreeing to store a copy but erasing it instead, refusing to serve a document, or serving an altered version of the document. We define a model of PIPE networks, a threat model for malicious sites, and propose basic solutions for managing these malicious sites. The basic solutions are inefficient, but demonstrate that a secure system can be built. We also sketch ways to improve the efficiency of the system.} } @TECHREPORT{Ganesan02 ,AUTHOR = "Prasanne Ganesan and Qixiang Sun and Hector Garcia-Molina" ,TITLE = "YAPPERS: A Peer-to-Peer Lookup Service Over Arbitrary Topology" ,INSTITUTION = "Stanford University" ,YEAR = "2002" ,number = "2002-24" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2002-24)" ,entered-by = "Rebecca Wesley" ,abstract = { Existing peer-to-peer search networks generally fall into two categories: Gnutella-style systems that use arbitrary topology and rely on controlled flooding for search, and systems that explicitly build an underlying topology to efficiently support a distributed hash table (DHT). In this paper, we propose a hybrid scheme for building a peer-to-peer lookup service over arbitrary network topology. Specifically, for each node in the search network, we build a small DHT consisting of nearby nodes and then provide an intelligent search mechanism that can traverse all the small DHTs. Our hybrid approach can reduce the nodes contacted for a lookup by an order of magnitude compared to Gnutella, allows rapid searching of nearby nodes through quick fan-out, does not reorganize the underlying overlay, and isolates the effect of topology changes to small areas for better scalability and stability.} } @INPROCEEDINGS{Datar02 ,AUTHOR = "Mayur Datar" ,TITLE = "Butterflies and Peer-to-Peer Networks" ,BOOKTITLE = esa02 ,YEAR = "2002" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2002-33)" ,entered-by = "Rebecca Wesley" ,abstract = {Research in Peer-to-peer systems has focussed on building efficient Content Addressable Networks (CANs), which are essentially distributed hash tables (DHT) that support location of resources based on unique keys. While most proposed schemes are robust to a large number of random faults, there are very few schemes that are robust to a large number of adversarial faults. In a recent paper Fiat and Saia have proposed such a solution that is robust to adversarial faults. We propose a new solution based on multi-butterflies that improves upon the previous solution by Fiat and Saia. Our new network, multi-hypercube, is a fault tolerant version of the hypercube, and may find applications to other problems as well. We also demonstrate how this network can be maintained dynamically. This addresses the first open problem in the paper by Fiat and Saia.} } @TECHREPORT{Cooperf01 ,AUTHOR = "Brian Cooper and Hector Garcia-Molina" ,TITLE = "Creating trading networks of digital archives" ,INSTITUTION = "Stanford University" ,YEAR = "2001" ,number = "2001-04" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2001-04)" ,entered-by = "Rebecca Wesley" ,abstract = {Digital archives can best survive failures if they have made several copies of their collections at remote sites. In this paper, we discuss how autonomous sites can cooperate to provide preservation by trading data. We examine the decisions that an archive must make when forming trading networks, such as the amount of storage space to provide and the best number of partner sites. We also deal with the fact that some sites may be more reliable than others. Experimental results from a data trading simulator illustrate which policies are most reliable.} } @TECHREPORT{Cooperg01 ,AUTHOR = "Brian Cooper and Hector Garcia-Molina" ,TITLE = "Creating trading networks of digital archives" ,INSTITUTION = "Stanford University" ,YEAR = "2001" ,number = "2001-23" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2001-23)" ,entered-by = "Rebecca Wesley" ,abstract = {Digital archives can best survive failures if they have made several copies of their collections at remote sites. In this paper, we discuss how autonomous sites can cooperate to provide preservation by trading data. We examine the decisions that an archive must make when forming trading networks, such as the amount of storage space to provide and the best number of partner sites. We also deal with the fact that some sites may be more reliable than others. Experimental results from a data trading simulator illustrate which policies are most reliable. Our techniques focus on preserving the ``bits'' of digital collections; other services that focus on other archiving concerns (such as preserving meaningful metadata) can be built on top of the system we describe here.} } @TECHREPORT{Yangh02 ,AUTHOR = "Beverly Yang and Hector Garcia-Molina" ,TITLE = "Designing a Super-Peer Network" ,INSTITUTION = "Stanford University" ,YEAR = "2002" ,number = "2002-13" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2002-13)" ,entered-by = "Rebecca Wesley" ,abstract = {A "super-peer" is a node in a peer-to-peer network that operates both as a server to a set of clients, and as an equal in a network of super-peers. Super-peer networks strike a balance between the inherent efficiency of centralized search, and the autonomy, load balancing and robustness to attacks provided by distributed search. Furthermore, they take advantage of the heterogeneity of capabilities (e.g., bandwidth, processing power) across peers, which recent studies have shown to be enormous. Hence, new and old P2P systems like Morpheus and Gnutella are adopting super-peers in their design. Despite their growing popularity, the behavior of super-peer networks is not well understood. For example, what are the potential drawbacks of super-peer networks? How can super-peers be made more reliable? How many clients should a super-peer take on to maximize efficiency? In this paper we examine super-peer networks in detail, gaining an understanding of their fundamental characteristics and performance tradeoffs. We also present practical guidelines and a general procedure for the design of an efficient super-peer network.} } @TECHREPORT{Grantk02 ,AUTHOR = "Karen D. Grant and Adrian Graham and Tom Nguyen and Andreas Paepcke and Terry Winograd" ,TITLE = "Beyond the Shoe Box: Foundations for Flexibly Organizing Photographs on a Computer" ,INSTITUTION = "Stanford University" ,YEAR = "2002" ,number = "2002-45" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2002-45)" ,entered-by = "Rebecca Wesley" ,abstract = { As a foundation for designing computer-supported photograph management tools, we have been conducting focused experiments. Here, we describe our analysis of how people initially organize batches of familiar images. We asked 26 subjects in pairs to organize 50 images on a common horizontal table. Each pair then organized a different 50-image set on a computer table of identical surface area. The bottom-projected computer tabletop displayed our interface to several online, pile-based affordances we wished to evaluate. Subjects used pens to interact with the system. We highlight aspects of the computer environment that were notably important to subjects, and others that they cared about less than we had hypothesized. For example, a strong majority preferred computer-generated representations of piles to be grid- shaped over several alternatives, some of which mimicked the physical world closely, and others that used transparency to save space.} } @TECHREPORT{Deshpandea01 ,AUTHOR = "Hrishikesh Deshpande and Mayank Bawa and Hector Garcia-Molina" ,TITLE = "Streaming Live Media over a Peer-to-Peer Network" ,INSTITUTION = "Stanford University" ,YEAR = "2001" ,number = "2001-31" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2001-31)" ,entered-by = "Rebecca Wesley" ,abstract = {The high bandwidth required by live streaming video greatly limits the number of clients that can be served by a source. In this work, we discuss and evaluate an architecture, called {\em SpreadIt}, for streaming live media over a network of clients, using the resources of the clients themselves. Using SpreadIt, we can distribute bandwidth requirements over the network. The key challenge is to allow an application level multicast tree to be easily maintained over a network of transient peers, while ensuring that quality of service does not degrade. We propose a basic peering infrastructure layer for streaming applications, which uses a redirect primitive to meet the challenge successfully. Through empirical and simulation studies, we show that SpreadIt provides a good quality of service, which degrades gracefully with increasing number of clients. Perhaps more significantly, existing applications can be made to work with SpreadIt, without any change to their code base. } } @TECHREPORT{Deshpandei01 ,AUTHOR = "Hrishikesh Deshpande and Mayank Bawa and Hector Garcia-Molina" ,TITLE = "Streaming Live Media over a Peer-to-Peer Network" ,INSTITUTION = "Stanford University" ,YEAR = "2001" ,number = "2001-30" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2001-30)" ,entered-by = "Rebecca Wesley" ,abstract = { The high bandwidth required by live streaming video greatly limits the number of clients that can be served by a source. In this work, we discuss and evaluate an architecture, called {\em SpreadIt}, for streaming live media over a network of clients, using the resources of the clients themselves. Using SpreadIt, we can distribute bandwidth requirements over the network. The key challenge is to allow an application level multicast tree to be easily maintained over a network of transient peers, while ensuring that quality of service does not degrade. We propose a basic peering infrastructure layer for streaming applications, which uses a redirect primitive to meet the challenge successfully. Through empirical and simulation studies, we show that SpreadIt provides a good quality of service, which degrades gracefully with increasing number of clients. Perhaps more significantly, existing applications can be made to work with SpreadIt, without any change to their code base. } } @TECHREPORT{Cooperb100 ,AUTHOR = "Brian Cooper and Hector Garcia-Molina" ,TITLE = "Peer to peer data trading to preserve information (Extended version)" ,INSTITUTION = "Stanford University" ,YEAR = "2000" ,number = "2000-38" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-38)" ,entered-by = "Rebecca Wesley" ,abstract = {Data archiving systems rely on replication to preserve information. In this paper, we discuss how a network of autonomous archiving sites can trade data to achieve the most reliable replication. A series of binary trades between sites produces a peer to peer archiving network. We examine two trading algorithms, one based on trading collections (even if they are different sizes) and another based on trading equal sized blocks of space (which can then store collections.) We introduce the concept of deeds, which track the sites that own space at other sites. We then discuss policies for tuning these algorithms to provide the highest reliability, for example by changing the order in which sites are contacted and offered trades. Finally, we present simulation results that reveal which policies are most reliable.} } @TECHREPORT{Cooperb200 ,AUTHOR = "Brian Cooper and Hector Garcia-Molina" ,TITLE = "Peer to peer data trading to preserve information" ,INSTITUTION = "Stanford University" ,YEAR = "2000" ,number = "2000-33" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2000-33)" ,entered-by = "Rebecca Wesley" ,abstract = {Data archiving systems rely on replication to preserve information. In this paper, we discuss how a network of autonomous archiving sites can trade data to achieve the most reliable replication. A series of binary trades between sites produces a peer to peer archiving network. We examine two trading algorithms, one based on trading collections (even if they are different sizes) and another based on trading equal sized blocks of space (which can then store collections.) We introduce the concept of deeds, which track the sites that own space at other sites. We then discuss policies for tuning these algorithms to provide the highest reliability, for example by changing the order in which sites are contacted and offered trades. Finally, we present simulation results that reveal which policies are most reliable.} } @TECHREPORT{Cooperb301 ,AUTHOR = "Brian Cooper and Hector Garcia-Molina" ,TITLE = "Bidding for storage space in a peer-to-peer data preservation system" ,INSTITUTION = "Stanford University" ,YEAR = "2001" ,number = "2001-52" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2001-52)" ,entered-by = "Rebecca Wesley" ,abstract = {Digital archives protect important data collections from failures by making multiple copies at other archives, so that there are always several good copies of a collection. In a cooperative replication network, sites ``trade'' space, so that each site contributes storage resources to the system and uses storage resources at other sites. Here, we examine bid trading: a mechanism where sites conduct auctions to determine who to trade with. A local site wishing to make a copy of a collection announces how much remote space is needed, and accepts bids for how much of its own space the local site must ``pay'' to acquire that remote space. We examine the best policies for determining when to call auctions and how much to bid, as well as the effects of ``maverick'' sites that attempt to subvert the bidding system. Simulations of auction and trading sessio ns indicate that bid trading can allow sites to achieve higher reliability than the alternative: a system where sites trade equal amounts of space without bidding.} } @TECHREPORT{Cooperb401 ,AUTHOR = "Brian Cooper and Hector Garcia-Molina" ,TITLE = "Peer to peer data trading to preserve information (Extended version)" ,INSTITUTION = "Stanford University" ,YEAR = "2001" ,number = "2001-6" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2001-6)" ,entered-by = "Rebecca Wesley" ,abstract = {Data archiving systems rely on replication to preserve information. In this paper, we discuss how a network of autonomous archiving sites can trade data to achieve the most reliable replication. A series of binary trades between sites produces a peer to peer archiving network. We examine two trading algorithms, one based on trading collections (even if they are different sizes) and another based on trading equal sized blocks of space (which can then store collections.) We introduce the concept of deeds, which track the sites that own space at other sites. We then discuss policies for tuning these algorithms to provide the highest reliability, for example by changing the order in which sites are contacted and offered trades. Finally, we present simulation results that reveal which policies are most reliable.} } @TECHREPORT{Cooperb501 ,AUTHOR = "Brian Cooper and Hector Garcia-Molina" ,TITLE = "Peer to peer data trading to preserve information" ,INSTITUTION = "Stanford University" ,YEAR = "2001" ,number = "2001-7" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2001-7)" ,entered-by = "Rebecca Wesley" ,abstract = {Data archiving systems rely on replication to preserve information. In this paper, we discuss how a network of autonomous archiving sites can trade data to achieve the most reliable replication. A series of binary trades between sites produces a peer to peer archiving network. We examine two trading algorithms, one based on trading collections (even if they are different sizes) and another based on trading equal sized blocks of space (which can then store collections.) We introduce the concept of deeds, which track the sites that own space at other sites. We then discuss policies for tuning these algorithms to provide the highest reliability, for example by changing the order in which sites are contacted and offered trades. Finally, we present simulation results that reveal which policies are most reliable.} } @TECHREPORT{Cooperb602 ,AUTHOR = "Brian Cooper and Hector Garcia-Molina" ,TITLE = "Bidding for storage space in a peer-to-peer data preservation system (Extended version)" ,INSTITUTION = "Stanford University" ,YEAR = "2002" ,number = "2002-22" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2002-22)" ,entered-by = "Rebecca Wesley" ,abstract = {Digital archives protect important data collections from failures by making multiple copies at other archives, so that there are always several good copies of a collection. In a cooperative replication network, sites ``trade'' space, so that each site contributes storage resources to the system and uses storage resources at other sites. Here, we examine bid trading: a mechanism where sites conduct auctions to determine who to trade with. A local site wishing to make a copy of a collection announces how much remote space is needed, and accepts bids for how much of its own space the local site must ``pay'' to acquire that remote space. We examine the best policies for determining when to call auctions and how much to bid, as well as the effects of ``maverick'' sites that attempt to subvert the bidding system. Simulations of auction and trading sessio ns indicate that bid trading can allow sites to achieve higher reliability than the alternative: a system where sites trade equal amounts of space without bidding.} } @TECHREPORT{Datarm02 ,AUTHOR = "Mayur Datar" ,TITLE = "Butterflies and Peer-to-Peer Networks" ,INSTITUTION = "Stanford University" ,YEAR = "2002" ,number = "2002-5" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2002-5)" ,entered-by = "Rebecca Wesley" ,abstract = {The popularity of systems like Napster, Gnutella etc. have spurred recent interest in Peer-to-peer systems. A central problem in all these systems is efficient location of resources based on their keys. A network that supports such queries is referred to as Content Addressable Network (CAN). Many solutions have been proposed to building CANs. However most of these solutions do not focus on adversarial faults, which might be critical to building a censorship resistant peer-to-peer system. In a recent paper Fiat and Saia have proposed a solution to building such a system. We propose a new solution based on multi-butterflies that improves upon the previous solution by Fiat and Saia. Our new network, (\bf multi-hypercube), is a fault tolerant version of hypercube. We also demonstrate how this network can be maintained dynamically. This addresses the first open problem in the paper by Fiat and Saia.} } @inproceedings{yee03a, author = {Ka-Ping Yee and Kirsten Swearingen and Kevin Li and Marti Hearst}, title = {Faceted metadata for image search and browsing}, booktitle = {Proceedings of the conference on Human factors in computing systems}, year = {2003}, isbn = {1-58113-630-7}, pages = {401--408}, location = {Ft. Lauderdale, Florida, USA}, doi = {http://doi.acm.org/10.1145/642611.642681}, publisher = {ACM Press}, entered-by = "Andreas Paepcke", abstract = {Introduces metadata 'facets'. Shows a simple interface for browsinig image collections that have multiple categories of metadata.} } @inproceedings{Rodd03, author = {Kerry Rodden and Kenneth R. Wood}, title = {How do people manage their digital photographs?}, booktitle = {Proceedings of the conference on Human factors in computing systems}, year = {2003}, isbn = {1-58113-630-7}, pages = {409--416}, location = {Ft. Lauderdale, Florida, USA}, doi = {http://doi.acm.org/10.1145/642611.642682}, publisher = {ACM Press}, entered-by = "Andreas Paepcke" } inproceedings{baud03, author = {Patrick Baudisch and Ruth Rosenholtz}, title = {Halo: a technique for visualizing off-screen objects}, booktitle = {Proceedings of the conference on Human factors in computing systems}, year = {2003}, isbn = {1-58113-630-7}, pages = {481--488}, location = {Ft. Lauderdale, Florida, USA}, doi = {http://doi.acm.org/10.1145/642611.642695}, publisher = {ACM Press}, entered-by = "Andreas Paepcke", keywords = "Halo, maps, navigation, peripheral awareness indicators, visualization, squeezable, small displays", abstract = {As users pan and zoom, display content can disappear into off-screen space, particularly on small-screen devices. The clipping of locations, such as relevant places on a map, can make spatial cognition tasks harder. Halo is a visualization technique that supports spatial cognition by showing users the location of off-screen objects. Halo accomplishes this by surrounding off-screen objects with rings that are just large enough to reach into the border region of the display window. From the portion of the ring that is visible on-screen, users can infer the off-screen location of the object at the center of the ring. We report the results of a user study comparing Halo with an arrow-based visualization technique with respect to four types of map-based route planning tasks. When using the Halo interface, users completed tasks 16-33% faster, while there were no significant differences in error rate for three out of four tasks in our study. } } @INPROCEEDINGS{cunningham03 ,AUTHOR = "Sally Jo Cunningham and Nina Reeves" ,TITLE = "An Ethnographic Study of Music Information Seeking: Implications for the Design of a Music Digital Library" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {At present, music digital library systems are being developed based on anecdotal evidence of user needs, intuitive feelings for user information seeking behavior, and a priori assumptions of typical usage scenarios. Emphasis has instead been placed on basic research into music document representation, efficient searching, and audio-based searching, rather than on exploring the music information needs or information behavior of a target user group. This paper focuses on eliciting the 'native' music information strategies employed by people searching for popular music (that is, music sought for recreational or enjoyment purposes rather than to support a 'serious' or scientific exploration of some aspect of music). To this end, we conducted an ethnographic study of the searching/browsing techniques employed by people in the researchers' local communities, as they use two common sources of music: the public library and music stores. We argue that the insights provided by this type of study can inform the development of searching/browsing support for music digital libraries.} } @INPROCEEDINGS{Medina03 ,AUTHOR = "Richard A. Medina and Lloyd A. Smith and Debra R. Wagner" ,TITLE = "Content-based Indexing of Musical Scores" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {Score-based music information retrieval (MIR) systems search databases of musical scores to find occurrences of a musical query pattern. Several such systems have been developed based on exhaustive approximate search of the database. Exhaustive search does not scale well, however, to large databases. This paper describes a method of automatically creating a content-based index of musical scores. The goal is to capture the themes, or motifs, that appear in the music. User queries, then, would be matched only over the index, rather than over the entire database. The method was tested by building an index of 25 orchestral movements from the classical music literature. For every movement, the system captured the primary theme, or a variation of the primary theme. In addition, it captured 13 of 28 secondary themes. The resulting index was 14% of the size of the database. By deleting musical patterns not found early in the music, it is possible to reduce the size of the index to 2% of the database; however, this method discards secondary themes. A listening experiment using five symphonic movements showed that people can reliably recognize secondary themes after listening to a piece of music therefore, it may be necessary to retain secondary themes in a score index.} } @INPROCEEDINGS{Chai03 ,AUTHOR = "Wei Chai and Barry Vercoe" ,TITLE = "Structural Analysis of Musical Signals for Indexing and Thumbnailing" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {A musical piece typically has a repetitive structure. Analysis of this structure will be useful for music segmentation, indexing and thumbnailing. This paper presents an algorithm that can automatically analyze the repetitive structure of musical signals. First, the algorithm detects the repetition of each segment of fixed length in a piece using dynamic programming. Second, the algorithm summarizes this repetition information and infers the structure based on heuristic rules. The performance of the approach is demonstrated visually using figures for qualitative evaluation, and by two structural similarity measures for quantitative evaluation. Based on the structural analysis result, this paper also proposes a method for music thumbnailing. The preliminary results obtained using a corpus of Beatles songs show that automatic structural analysis and thumbnailing of music are possible.} } @INPROCEEDINGS{Han03 ,AUTHOR = "Hui Han and C. Lee Giles and Eren Manavoglu and Hongyuan Zha and Zhenyue Zhang and Edward A. Fox" ,TITLE = "Automatic Document Metadata Extraction using Support Vector Machines" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {Automatic metadata generation provides scalability and usability for digital libraries and their collections. Machine learning methods offer robust and adaptable automatic metadata extraction. We describe a support vector machine classification-based method for metadata extraction from the header part of the research papers and show that it outperforms other machine learning methods on the same task. The method first classifies each line of the header into one or more of the 15 classes. An iterative convergence procedure is then used to improve the line classification by using the predicted class labels of its neighbor lines in the previous round. Further metadata extraction is done by seeking the best chunk boundaries of each line. We found that discovery and use of the structural patterns of the data and domain based feature selection can improve the metadata extraction performance. An appropriate feature normalization also greatly improves the classification performance.} } @INPROCEEDINGS{Takasu03 ,AUTHOR = "Atsuhiro Takasu" ,TITLE = "Bibliographic Attribute Extraction from Erroneous References Based on a Statistical Model" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {This paper proposes a method for extracting bibliographic attributes from OCR processed reference strings using an extended hidden Markov model. Bibliographic attribute extraction can be used in two ways. One is reference parsing in which attribute values are extracted from OCR processed reference for bibliographic matching. The other is reference alignment in which attribute values are aligned to the bibliographic record for enriching the vocabulary of the bibliographic database. In this paper, we first propose a statistical model for the attribute extraction which represents both syntactical structure of references and Optical Character Recognition (OCR) error patterns. Then, we perform experiments using bibliographic references obtained from scanned images of papers in journals and transactions and show that useful attribute values are extracted from OCR processed references with the accuracy of 93.9%. We also show that the proposed model has advantages in reducing the cost of preparing training data, which is a critical problem in rule-based systems.} } @INPROCEEDINGS{Soo03 ,AUTHOR = "Von-Wun Soo and Chen-Yu Lee and Chung-Cheng Lin and Shu Lei Chen and Ching-chih Chen." ,TITLE = "Automated Semantic Annotation and Retrieval Based on Sharable Ontology and Case-based Learning Techniques" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {Effective information retrieval (IR) using domain knowledge and semantics is one of major challenges in IR. In this paper we propose a framework that can facilitate the image retrieval based on the sharable domain ontology and thesaurus. In particular, a case-based learning (CBL) using natural language phrase parser is proposed to convert a natural language query into a resource description framework (RDF) format, a semantic-web standard of metadata description that supports machine readable semantic representation. This same parser is also extended to perform the semantic annotation on the descriptive metadata of images and convert metadata automatically into the same RDF representation. The retrieval of images can then be conducted by matching the semantic and structural descriptions of the user query with those of the annotated descriptive metadata of images. We tested our problem domain by retrieving the historical and cultural images taken from Dr. Ching-chih Chen "First Emperor of China" CD-ROM as part of our productive international digital library collaboration. We have constructed and implemented the domain ontology, a Mandarin Chinese thesaurus, as well as the similarity match and retrieval algorithms in order to test our proposed framework. Our experiments have shown the feasibility and usability of these approaches.} } @INPROCEEDINGS{Crane03 ,AUTHOR = "Gregory Crane and Clifford E. Wulfman and Lisa M. Cerrato and Anne Mahoney and Thomas L. Milbank and David Mimno and Jeffrey A. Rydberg-Cox and David A. Smith and Christopher York" ,TITLE = "Towards a Cultural Heritage Digital Library" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {This paper surveys research areas relevant to cultural heritage digital libraries. The emerging National Science Digital Library promises to establish the foundation on which those of us beyond the scientific and engineering community will likely build. This paper thus articulates the particular issues that we have encountered in developing cultural heritage collections. We provide a broad overview of audiences, collections, and services.} } @INPROCEEDINGS{Tansley03 ,AUTHOR = "Robert Tansley and Mick Bass and David Stuve and Margret Branschofsky and Daniel Chudnov and Greg McClellan and MacKenzie Smith" ,TITLE = "DSpace: An Institutional Digital Repository System" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {In this paper we describe DSpace ., an open source system that acts as a repository for digital research and educational material produced by an organization or institution. DSpace was developed during two years. collaboration between the Hewlett-Packard Company and MIT Libraries. The development team worked closely with MIT Libraries staff and early adopter faculty members to produce a .breadth-first. system, providing all of the basic features required by a digital storage and preservation service. We describe the functionality of the current DSpace system, and briefly describe its technical architecture. We conclude with some remarks about the future development and operation of the DSpace system.} } @INPROCEEDINGS{Anderson03 ,AUTHOR = "Kenneth M. Anderson and Aaron Andersen and Neet Wadhwani and Laura M. Bartolo" ,TITLE = "Metis: Lightweight, Flexible, and Web-based Workflow Services for Digital Libraries" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {The Metis project is developing workflow technology designed for use in digital libraries by avoiding the assumptions made by traditional workflow systems. In particular, digital libraries have highly distributed sets of stakeholders who nevertheless must work together to perform shared activities. Hence, traditional assumptions that all members of a workflow belong to the same organization, work in the same fashion, or have access to similar computing platforms are invalid. The Metis approach makes use of event-based workflows to support the distributed nature of digital library workflow and employs techniques to make the resulting technology lightweight, flexible, and integrated with the Web. This paper describes the conceptual framework behind the Metis approach as well as a prototype which implements the framework. The prototype is evaluated based on its ability to model and execute a workflow drawn from a "real-world" digital library. After describing related work, the paper concludes with a discussion of future research opportunities in the area of digital library workflow and outlines how Metis is being deployed to a small set of digital libraries for additional evaluation.} } @INPROCEEDINGS{Fu03 ,AUTHOR = "Yueyu Fu Javed Mostafa and Kazuhiro Seki" ,TITLE = "Protein Association Discovery in Biomedical Literature [short paper] " ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {Protein association discovery can directly contribute toward developing protein pathways; hence it is a significant problem in bioinformatics. LUCAS (Library of User-Oriented Concepts for Access Services) was designed to automatically extract and determine associations among proteins from biomedical literature. Such a tool has notable potential to automate database construction in biomedicine, instead of relying on experts' analysis. This paper reports on the mechanisms for automatically generating clusters of proteins. A formal evaluation of the system, based on a subset of 2000 MEDLINE titles and abstracts, has been conducted against Swiss-Prot database in which the associations among concepts are entered by experts manually.} } @INPROCEEDINGS{Leroy03 ,AUTHOR = "Gondy Leroy and Hsinchun Chen and Jesse D. Martinez and Shauna Eggers and Ryan Falsey and Kerri Kislin and Zan Huang and Jiexun Li and Jie Xu and Daniel McDonald and Gavin Ng " ,TITLE = "Genescene: Biomedical Text And Data Mining [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {To access the content of digital texts efficiently, it is necessary to provide more sophisticated access than keyword based searching. Genescene provides biomedical researchers with research findings and background relations automatically extracted from text and experimental data. These provide a more detailed overview of the information available. The extracted relations were evaluated by qualified researchers and are precise. A qualitative ongoing evaluation of the current online interface indicates that this method to search the literature is more useful and efficient than keyword based searching.} } @INPROCEEDINGS{Pomerantz03 ,AUTHOR = "Jeffrey Pomerantz and R. David Lankes " ,TITLE = "Taxonomies for Automated Question Triage in Digital Reference [short paper] " ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {This study identifies (1) several taxonomies of questions at different levels of linguistic analysis, according to which questions received by digital reference services are classified, and (2) a simple categorization of triage recipients. The utility of these taxonomies and categorizations of is discussed as the basis for systems for automating triage and other steps in the digital reference process.} } @INPROCEEDINGS{Kurtz03 ,AUTHOR = "Andrew J. Kurtz and Javed Mostafa" ,TITLE = "Topic Detection and Interest Tracking in a Dynamic Online News Source [short paper] " ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {Digital libraries in the news domain may contain frequently updated data. Providing personalized access to such dynamic resources is an important goal. In this paper, we investigate the area of filtering online dynamic news sources based on personal profiles. We experimented with an intelligent news-sifting system that tracks topic development in a dynamic online news source. Vocabulary discovery and clustering are used to expose current news topics. User interest profiles, generated from explicit and implicit feedback are used to customize the news retrieval system's interface.} } @INPROCEEDINGS{Davis03 ,AUTHOR = "Peter T. Davis and David K. Elson and Judith L. Klavans " ,TITLE = "Methods for Precise Named Entity Matching in Digital Collections [short paper] " ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {In this paper, we describe an interactive system. built within the context of CLiMB project, which permits a user to locate the occurrences of named entities within a given text. The named entity tool was developed to identify references to a single art object (e.g. a particular building) with high precision in text related to images of that object in a digital collection. We start with an authoritative list of art objects, and seek to match variants of these named entities in related text. Our approach is to "decay" entities into progressively more general variants while retaining high precision. As variants become more general, and thus more ambiguous, we propose methods to disambiguate intermediate results. Our results will be used to select records into which automatically generated metadata will be loaded.} } @INPROCEEDINGS{French03 ,AUTHOR = "James C. French and A. C. Chapin and Worthy N. Martin" ,TITLE = "An Application of Multiple Viewpoints to Content-Based Image Retrieval [short paper] " ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {Content-based image retrieval uses features that can be extracted from the images themselves. Using more than one representation of the images in a collection can improve the results presented to a user without changing the underlying feature extraction of search technologies. We present an example of this "multiple viewpoint" approach, multiple image channels. and discuss its advantages for an image-seeking user. This approach has also been shown to dramatically improve retrieval effectiveness in content-based image retrieval systems.} } @INPROCEEDINGS{Marshall03 ,AUTHOR = "Byron Marshall and Yiwen Zhang and Hsinchun Chen and Ann Lally and Edward Fox" ,TITLE = "Convergence of Knowledge Management and E-Learning: the GetSmart Experience" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {The National Science Digital Library (NSDL), launched in December 2002, is emerging as a center of innovation in digital libraries as applied to education. As a part of this extensive project, the GetSmart system was created to apply knowledge management techniques in a learning environment. The design of the system is based on an analysis of learning theory and the information search process. Its key notion is the integration of search tools and curriculum support with concept mapping. More than 100 students at the University of Arizona and Virginia Polytechnic Institute used the system in the fall of 2002. A database of more than one thousand student-prepared concept maps has been collected with more than forty thousand relationships expressed in semantic, graphical, node-link representations. Preliminary analysis of the collected data is revealing interesting knowledge representation patterns.} } @INPROCEEDINGS{Rowe03 ,AUTHOR = "Jeremy Rowe and Anshuman Razdan and Arleyn Simon" ,TITLE = "Acquisition, Representation, Query and Analysis of Spatial Data: A Demonstration 3D Digital Library" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {The increasing power of techniques to model complex geometry and extract meaning from 3D information create complex data that must be described, stored, and displayed to be useful to researchers. Responding to the limitations of two-dimensional (2D) data representations perceived by discipline scientists, the Partnership for Research in Spatial Modeling (PRISM) project at Arizona State University (ASU) developed modeling and analytic tools that raise the level of abstraction and add semantic value to 3D data. The goals are to improve scientific communication, and to assist in generating new knowledge, particularly for natural objects whose asymmetry limit study using 2D representations. The tools simplify analysis of surface and volume using curvature and topology to help researchers understand and interact with 3D data. The tools produced automatically extract information about features and regions of interest to researchers, calculate quantifiable, replicable metric data, and generate metadata about the object being studied. To help researchers interact with the information, the project developed prototype interactive, sketch-based interfaces that permit researchers to remotely search, identify and interact with the detailed, highly accurate 3D models of the objects. The results support comparative analysis of contextual and spatial information, and extend research about asymmetric man-made and natural objects.} } @INPROCEEDINGS{McKeown03 ,AUTHOR = "Kathleen R. McKeown and Noemie Elhadad and Vasileios Hatzivassiloglou" ,TITLE = "Leveraging a Common Representation for Personalized Search and Summarization in a Medical Digital Library" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {Despite the large amount of online medical literature, it can be difficult for clinicians to find relevant information at the point of patient care. In this paper, we present techniques to personalize the results of search, making use of the online patient record as a sophisticated, pre-existing user model. Our work in PERSIVAL, a medical digital library, includes methods for re-ranking the results of search to prioritize those that better match the patient record. It also generates summaries of the re-ranked results which highlight information that is relevant to the patient under the physician's care. We focus on the use of a common representation for the articles returned by search and the patient record which facilitates both the re-ranking and the summarization tasks. Taken together, this common approach to both tasks has a strong positive effect on the amount of personalization which is possible.} } @INPROCEEDINGS{Monroy03 ,AUTHOR = "Carlos Monroy and Richard Furuta and Enrique Mallen " ,TITLE = "Visualizing and Exploring Picasso's World [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {We discuss the preliminary use of a visualization tool called Interactive Timeline Viewer (ItLv) in visualizing and exploring a collection of art works by Pablo Ruiz Picasso. Our data set is composed of a subset of the Online Picasso Project, a significantly-sized on-line art repository of the renowned Spanish artist. We also include a brief discussion about how this visualization tool can help art scholars to study and analyze an artist's life and works.} } @INPROCEEDINGS{Johnson03 ,AUTHOR = "Heidi Johnson" ,TITLE = "Graded Access to Sensitive Materials at the Archive of the Indigenous Languages of Latin America [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {The Archive of the Indigenous Languages of Latin America (AILLA) is a web-accessible repository of multi-media resources in and about the indigenous languages of Latin America. In this paper, I describe the Graded Access System developed at AILLA to protect sensitive materials by allowing resource producers - academics and indigenous people - finely-grained control over the resources they house in the archive.} } @INPROCEEDINGS{Southwick03 ,AUTHOR = "Slvia Barcellos Southwick and Richard Southwick " ,TITLE = "Learning Digital Library Technology Across Borders [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {This paper describes the background context and initial findings from an ongoing case study of an electronic theses and dissertations (ETD) digital library (DL) project in Brazil. The specific focus of the case study centers on the activities of a Brazilian government agency acting as a mediator between software developers - primarily academic institutions in the United States - and university clients in Brazil. The authors highlight the loosely integrated nature of the DL technology, and the uncertain relationship between developers and users in terms of support. These circumstances reinforce a view of technology transfer as a process of organizational learning. As a consequence, the mediating institution in the study is viewed as assuming multiple roles in advancing the project.} } @INPROCEEDINGS{Reyes03 ,AUTHOR = " Natalia Reyes-Farfn and Alfredo Snchez" ,TITLE = "Personal Spaces in the Context of the OAI Initiative [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {We describe MiBiblio 2.0 a highly personalizable user interface for a federation of digital libraries under the OAI Protocol for Metadata Harvesting. (OAI-PMH). MiBiblio 2.0 allows users to personalize their personal space by choosing the resources and services they need, as well as to organize, classify and manage their workspaces including resources from any of the federated libraries. Results can be kept in personal spaces and organized into categories using a drag-and-drop interface.} } @INPROCEEDINGS{Castellanos03 ,AUTHOR = "Nohema Castellanos and Alfredo Snchez" ,TITLE = "PoPS: Mobile Access to Digital Library Resources [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {Mobile devices represent new opportunities for accessing digital libraries (DLs) but also pose a number of challenges given the diversity of their hardware and software features. We describe a framework aimed at facilitating the generation of interfaces for access to DL resources from a wide range of mobile devices.} } @INPROCEEDINGS{Chu03 ,AUTHOR = "Yi-Chun Chu and Ian H. Witten and Richard Lobb and David Bainbridge" ,TITLE = "How to turn the page [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {Can digital libraries provide a reading experience that more closely resembles a real book than a scrolled or paginated electronic display? This paper describes a prototype page-turning system that realistically animates full three-dimensional page-turns. The dynamic behavior is generated by a mass-spring model defined on a rectangular grid of particles. The prototype takes a PDF or E-book file, renders it into a sequence of PNG images representing individual pages, and animates the pageturns under user control. The simulation behaves fairly naturally, although more computer graphics work is required to perfect it.} } @INPROCEEDINGS{Liux03 ,AUTHOR = "Xiaoming Liu and Kurt Maly and Mohammad Zubair and Michael Nelson" ,TITLE = "Repository Synchronization in the OAI Framework" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {The Open Archives Initiative Protocol for Metadata Harvesting (OAI-PMH) began as an alternative to distributed searching of scholarly eprint repositories. The model embraced by the OAI-PMH is that of metadata harvesting, where value-added services (by a ``service provider'') are constructed on cached copies of the metadata extracted from the repositories of the harvester's choosing. While this model dispenses with the well known problems of distributed searching, it introduces the problem of synchronization. Stated simply, this problem arises when the service provider's copy of the metadata does not match the metadata currently at the constituent repositories. We define some metrics for describing the synchronization problem in the OAI-PMH. Based on these metrics, we study the synchronization problem of the OAI-PMH framework and propose several approaches for harvesters to implement better synchronization. In particular, if a repository knows its update frequency, it can publish it in an OAI-PMH Identify response using an optional About container that borrows from RDF Site Syndication (RSS) Format.} } @INPROCEEDINGS{Petinot03 ,AUTHOR = "Yves Petinot and Pradeep B. Teregowda and Hui Han and C. Lee Giles and Steve Lawrence and Arvind Rangaswamy" ,TITLE = "eBizSearch: An OAI-Compliant Digital Library for eBusiness" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {Niche Search Engines offer an efficient alternative to traditional search engines when the results returned by general-purpose search engines do not provide a sufficient degree of relevance and when nontraditional search features are required. Niche search engines can take advantage of their domain of concentration to achieve higher relevance and offer enhanced features. We discuss a new digital library niche search engine, eBizSearch, dedicated to e-business and e-business documents. The ground technology for eBizSearch is CiteSeer, a special-purpose automatic indexing document digital library and search engine developed at NEC Research Institute. We present here the integration of CiteSeer in the framework of eBizSearch and the process necessary to tune the whole system towards the specific area of e-business. We also discuss how using machine learning algorithms we generate metadata to make eBizSearch Open Archives compliant. eBizSearch is a publicly available service and can be reached at [EBIZ].} } @INPROCEEDINGS{Hochstenbach03 ,AUTHOR = "Patrick Hochstenbach and Henry Jerez and Herbert Van de Sompel" ,TITLE = "The OAI-PMH Static Repository and Static Repository Gateway" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {Although the OAI-PMH specification is focused on making it straightforward for data providers to expose metadata, practice shows that in certain significant situations deployment of OAI-PMH conformant repository software remains problematic. In this paper, we report on research aimed at devising solutions to further lower the barrier to make metadata collections harvestable. We provide an in depth description of an approach in which a data provider makes a metadata collection available as an XML file with a specific format an OAI Static Repository which is made OAI-PMH harvestable through the intermediation of software an OAI Static Repository Gateway - operated by a third party. We describe the properties of both components, and provide insights in our experience with an experimental implementation of a Gateway.} } @INPROCEEDINGS{Wildemuth03 ,AUTHOR = "Barbara M. Wildemuth and Gary Marchionini and Meng Yang and Gary Geisler and Todd Wilkens and Anthony Hughes and Richard Gruss" ,TITLE = "How fast is too fast? Evaluating fast forward surrogates for digital video" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {Because the number of libraries incorporating digital video is rapidly increasing, there is a crucial need for more effective user interfaces to access these materials. To support effective browsing, such interfaces should include video surrogates (i.e., smaller objects that can stand in for the videos in the collection, analogous to abstracts standing in for documents). The current study investigated four variations (i.e., speeds) of one form of video surrogate: a fast forward of the video created by selecting every Nth frame from the full video. In addition, it provided a field test of the validity of six measures of user performance when interacting with video surrogates. Forty-five study participants interacted with all four versions of the fast forward surrogate, and completed all six performance tasks with each surrogate. Surrogate speed affected performance on four measures: object recognition (graphical), action recognition, linguistic gist comprehension (full text), and visual gist comprehension. Based on these results, we recommend that the default speed for fast forward surrogates should be about 1:64 of the original video keyframes. In addition, users should control the choice of fast forward speed to adjust for content characteristics and personal preferences.} } @INPROCEEDINGS{Kholief03 ,AUTHOR = "Mohamed Kholief and Kurt Maly and Stewart Shen" ,TITLE = "Event-Based Retrieval from a Digital Library containing Medical Streams [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {We describe a digital library that contains streams and supports event-based retrieval. Streams used in the digital library are CT scan, medical text, and audio streams. Events, such as 'tumor appeared', were generated and represented in the user interface to enable doctors to retrieve and playback segments of the streams. This paper concentrates on describing the data organization and the user interface.} } @INPROCEEDINGS{Byrd03 ,AUTHOR = "Donald Byrd and Eric Isaacson " ,TITLE = "Music Representation in a Digital Music Library [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {The Variations2 digital music library currently supports music in audio and score-image formats. In a future version, we plan to add music in a symbolic form. This paper describes our work defining a music representation suitable for the needs of our users.} } @INPROCEEDINGS{Gurijala03 ,AUTHOR = "Aparna Gurijala and J.R. Deller, Jr. " ,TITLE = "A quantified fidelity criterion for parameter-embedded watermarking of audio archives [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {A novel algorithm for speech watermarking through parametric modeling is enhanced by inclusion of a quantified fidelity criterion. Watermarking is effected through solution of a set-membership filtering (SMF) problem, subject to an l(infinity) fidelity criterion in the signal space. The SMF approach provides flexibility in obtaining watermark solutions that trade-off watermark robustness and stegosignal fidelity.} } @INPROCEEDINGS{Sanchez03 ,AUTHOR = "J. Alfredo Snchez and Anbal Arias" ,TITLE = "Fourth-Phase Digital Libraries: Pacing, Linking, Annotating and Citing in Multimedia Collections [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {We discuss the implications of the use of current multimedia collections and posit that it is possible to build what we term fourth-phase digital libraries (4PDLs). In 4PDLs users can take advantage of both the powerful audiovisual channels and the proven practices developed for media such as text. We demonstrate how various technologies can be integrated to produce a 4PDL.} } @INPROCEEDINGS{Liuz03 ,AUTHOR = "Zehua Liu and Ee-Peng Lim and Wee-Keong Ng and Dion H. Goh" ,TITLE = "On Querying Geospatial and Georeferenced Metadata Resources in GPortal" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {G-Portal is a web portal system providing a range of digital library services to access geospatial and georeferenced re- sources on the Web. Among them are the storage and query subsystems that provide a central repository of metadata resources organized under different projects. In G-Portal, all metadata resources are represented in XML (Extensible Markup Language) and they are compliant to some resource schemas defined by their creators. The resource schemas are extended versions of a basic resource schema making it easy to accommodate all kinds of metadata resources while maintaining the portability of resource data. To support queries over the geospatial and georeferenced metadata re- sources, a XQuery-like query language known as RQL (Re- source Query Language) has been designed. In this paper, we present the RQL language features and provide some experimental findings about the storage design and query evaluation strategies for RQL queries.} } @INPROCEEDINGS{Ferebee03 ,AUTHOR = "Michelle Ferebee and Greg Boeshaar and Kathryn Bush and Judy Hertz" ,TITLE = "A Scientific Digital Library in Context: An Earth Radiation Budget Experiment Collection in the Atmospheric Sciences Data Center Digital Library [short paper] " ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {At the NASA Langley Research Center, the Earth Radiation Budget Experiment (ERBE) Data Management Team and the Atmodpheric Sciences Data Center are developing a digital collection for the ERBE project. The main goal is long-term preservation of a comprehensive information environment. The secondary goal is to provide a context for these data products by centralizing the 25 year research project's scattered information elements. The development approach incorporates elements of rapid prototyping and user-centered design in a standards-based implementation. A working prototype is in testing with a small number of users.} } @INPROCEEDINGS{Sumnera03 ,AUTHOR = "Tamara Sumner and Sonal Bhushan and Faisal Ahmad " ,TITLE = "Designing a Language for Creating Conceptual Browsing Interfaces for Digital Libraries [short paper] " ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {Conceptual browsing interfaces can help educators and learners to locate and use learning resources in educational digital libraries; in particular, resources that are aligned with nationally-recognized learning goals. Towards this end, we are developing a Strand Map Library Service, based on the maps published by the American Association for the Advancement of Science (AAAS). This service includes two public interfaces: (1) a graphical user interface for use by teachers and learners and (2) a programmatic interface that enables developers to construct conceptual browsing interfaces using dynamically generated components. Here, we describe our iterative, rapid prototyping design methodology, and the initial round of language type components that have been implemented and evaluated.} } @INPROCEEDINGS{Janee03 ,AUTHOR = "Greg Janee and James Frew and David Valentine" ,TITLE = "Content Access Characterization in Digital Libraries [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {To support non-trivial clients, such as data exploration and analysis environments, digital libraries must be able to describe the access modes that their contents support. We present a simple scheme that distinguishes four content accessibility classes: download (byte-stream retrieval), service (API), web interface (interactive), and alternative (semantically equivalent) or multipart (component) hierarchies. This scheme is simple enough to be easily supported by DL content providers, yet rich enough to allow programmatic clients to automatically identify appropriate access point(s).} } @INPROCEEDINGS{Yes03 ,AUTHOR = "Song Ye and Fillia Makedon and Tilmann Steinberg and Li Shen and Yuhang Wang and Yan Zhao and James Ford " ,TITLE = "SCENS: a System for the Mediated Sharing of Sensitive Data [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {This paper introduces SCENS, a Secure Content Exchange Negotiation System suitable for the exchange of private digital data that reside in distributed digital repositories. SCENS is an open negotiation system with flexibility, security and scalability. SCENS is currently being designed to support data sharing in scientific research, by providing incentives and goals specific to a research community. However, it can easily be extended to apply to other communities, such as government, commercial and other types of exchanges. It is a trusted third party software infrastructure enabling independent entities to interact and conduct multiple forms of negotiation.} } @INPROCEEDINGS{Sumnerb03 ,AUTHOR = "Tamara Sumner and Michael Khoo and Mimi Recker and Mary Marlino" ,TITLE = "Understanding Educator Perceptions of 'Quality' in Digital Libraries" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {The purpose of the study was to identify educators' expectations and requirements for the design of educational digital collections for classroom use. A series of five focus groups was conducted with practicing teachers, pre-service teachers, and science librarians, drawn from different educational contexts (i.e., K-5, 6-12, College). Participants' expect that the added value of educational digital collections is the provision of: (1) 'high quality' teaching and learning resources, and (2) additional contextual information beyond that in the resource. Key factors that influence educators' perceptions of quality were identified: scientific accuracy, bias, advertising, design and usability, and the potential for student distraction. The data showed that participants judged these criteria along a continuum of tolerance, combining consideration of several factors in their final judgements. Implications for collections accessioning policies, peer review, and digital library service design are discussed.} } @INPROCEEDINGS{Oldenettel03 ,AUTHOR = "Frank Oldenettel and Michael Malachinski" ,TITLE = "Integrating digital libraries into learning environments: The LEBONED Approach" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {This paper presents the project LEBONED that focuses on the integration of digital libraries and their contents into web-based learning environments. We describe in general how the architecture of a standard learning management system has to be modified to enable the integration of digital libraries. An important part of this modification is the 'LEBONED Metadata Architecture' which depicts the handling of metadata and documents imported from digital libraries. The main components of this architecture and their interrelation are presented in detail. Afterwards we show a practical application of the concepts described before: The integration of the digital library 'eVerlage' into the learning environment 'Blackboard'.} } @INPROCEEDINGS{Mu03 ,AUTHOR = "Xiangming Mu and Gary Marchionini and Amy Pattee" ,TITLE = "The Interactive Shared Educational Environment: User Interface, System Architecture and Field Study" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {The user interface and system architecture of a novel Interactive Shared Educational Environment (ISEE) are presented. Based on a lightweight infrastructure, ISEE enables relatively low bandwidth network users to share videos as well as the text messages. Smartlink is a new concept introduced in this paper. Individual information presentation components, like the video player and text chat room, are smartly linked together through video timestamps and hyperlinks. A field study related to children book selections using ISEE was conducted. The results indicated that the combination of three information presentation components, including video player with storyboard, shared browser, and text chat room, provided an effective and more comfortable collaboration and learning environment for the given tasks than text reviews or text chat alone or in combination. The video player was the most preferred information component. Text abstract in the chat room that did not synchronize with the video content distracted some participants due to limited cognitive capacity. Using smartlink to synchronize various information components or channels is our attempt to reduce the users working memory load in information enriched distance learning environments made possible by digital libraries.} } @INPROCEEDINGS{Renear03 ,AUTHOR = "Allen Renear and Dave Dubin and Michael Sperberg-McQueen and Claus Huitfeldt " ,TITLE = "XML Semantics and Digital Libraries [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {The lack of a standard formalism for expressing the semantics of an XML vocabulary is a major obstacle to the development of high-function interoperable digital libraries. XML document type definitions (DTDs) provide a mechanism for specifying the syntax of an XML vocabulary, but there is no comparable mechanism for specifying the semantics of that vocabulary - where semantics simply means the basic facts and relationships represented by the occurrence of XML constructs. A substantial loss of functionality and interoperability in digital libraries results from not having a common machine-readable formalism for expressing these relationships for the XML vocabularies currently being used to encode content. Recently a number of projects and standards have begun taking up related topics. We describe the problem and our own project.} } @INPROCEEDINGS{Shreeves03 ,AUTHOR = "Sarah L. Shreeves and Christine Kirkham and Joanne Kaczmarek and Timothy W. Cole" ,TITLE = "Utility of an OAI Service Provider Search Portal [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {The Open Archive Initiative (OAI) Protocol for Metadata Harvesting (PMH) facilitates efficient interoperability between digital collections, in particular by enabling service providers to construct, with relatively modest effort, search portals that present aggregated metadata to specific communities. This paper describes the experiences of the University of Illinois at Urbana-Champaign Library as an OAI service provider. We discuss the creation of a search portal to an aggregation of metadata describing cultural heritage resources. We examine several key challenges posed by the aggregated metadata and present preliminary findings of a pilot study of the utility of the portal for a specific community (student teachers). We also comment briefly on the potential for using text analysis tools to uncover themes and relationships within the aggregated metadata.} } @INPROCEEDINGS{Harrison03 ,AUTHOR = "Terry L. Harrison and Michael L. Nelson and Mohammad Zubair " ,TITLE = "The Dienst-OAI Gateway [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {Though the Open Archive Initiative Protocol for Metadata Harvesting (OAI-PMH) is becoming the de facto standard for digital libraries, some of its predecessors are still in use. Although a limited number of Dienst repositories continue to be populated, others are precariously unsupported. The Dienst Open Archive Gateway (DOG) is a gateway between the OAI-PMH and the Dienst (version 4.1) protocol. DOG allows OAI-PMH harvesters to extract metadata records (in RFC-1807 or Dublin Core) from Dienst servers.} } @INPROCEEDINGS{Goncalver03 ,AUTHOR = "Marcos Andr Gonalves and Ganesh Panchanathan and Unnikrishnan Ravindranathan and Aaron Krowne and Edward A. Fox and Filip Jagodzinski and Lillian Cassel " ,TITLE = "The XML Log Standard for Digital Libraries: Analysis, Evolution, and Deployment [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {We describe current efforts and developments building on our proposal for an XML log standard format for digital library (DL) logging analysis and companion tools. Focus is given to the evolution of formats and tools based on analysis of deployment in several DL systems and testbeds. Recent development of analysis tools also is discussed.} } @INPROCEEDINGS{Ward03 ,AUTHOR = "Jewel H. Ward " ,TITLE = "A Quantitative Analysis of Dublin Core Metadata Element Set Usage within OAI Data Providers [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {This research describes an empirical study of how the unqualified Dublin Core Metadata Element Set (DC or DCMES) is used by 100 Data Providers (DPs) registered with the Open Archives Initiative (OAI). The research was conducted to determine whether or not the DCMES is used to its full capabilities. Eighty-two of 100 DPs have metadata records available for analysis. DCMES usage varies by type of DP. The average number of Dublin Core elements per record is eight, with an average of 91,785 Dublin Core elements in each DP. Five of the 15 elements of the DCMES are used 71% of the time. The results show the unqualified DCMES is not used to its fullest extent within DPs registered with the OAI.} } @INPROCEEDINGS{Milbank03 ,AUTHOR = "Thomas L. Milbank " ,TITLE = "Extracting Geometry from Digital Models in a Cultural Heritage Digital Library [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {This paper describes research to enhance the integration between digital models and the services provided by the document management systems of digital libraries. Processing techniques designed for XML texts are applied to X3D models, allowing specific geometry to be automatically retrieved and displayed. The research demonstrates that models designed on object-oriented paradigms are most easily exploited by XML document management systems.} } @INPROCEEDINGS{Bainbridge03 ,AUTHOR = "David Bainbridge and John Thompson and Ian H. Witten" ,TITLE = "Assembling and enriching digital library collections" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {People who create digital libraries need to gather together the raw material, add metadata as necessary, and design and build new collections. This paper sets out the requirements for these tasks and describes a new tool that supports them interactively, making it easy for users to create their own collections from electronic files of all types. The process involves selecting documents for inclusion, coming up with a suitable metadata set, assigning metadata to each document or group of documents, designing the form of the collection in terms of document formats, searchable indexes, and browsing facilities, building the necessary indexes and data structures, and putting the collection in place for others to use. All these tasks are supported within a modern point-and-click interaction paradigm. Although the tool is specific to the Greenstone digital library software, the underlying ideas should prove useful in more general contexts.} } @INPROCEEDINGS{Castelli03 ,AUTHOR = "Donatella Castelli and Pasquale Pagano" ,TITLE = "A System for Building Expandable Digital Libraries" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {Expandability is one of the main requirements of future digital libraries. This paper introduces a digital library service system, OpenDLib, that has been designed to be highly expandable both in terms of content, services and usage. The paper illustrate the mechanisms that enable expandability and discusses their impact on the development of the system architecture.} } @INPROCEEDINGS{Calado03 ,AUTHOR = "Pvel P. Calado and Marcos A.Gonalves and Edward A. Fox and Berthier Ribeiro-Neto and Alberto H. F. Laender and Altigran S.da Silva and Davi C.Reis and Pablo A. Roberto and Monique V. Vieira and Juliano P. Lage" ,TITLE = "The Web-DL Environment for Building Digital Libraries from the Web" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {The Web contains a huge volume of unstructured data, which is difficult to manage. In digital libraries, on the other hand, information is explicitly organized, described, and managed. Community-oriented services are built to attend specific information needs and tasks. In this paper, we describe an environment, Web-DL, that allows the construction of digital libraries from the Web. The Web-DL environment will allow us to collect data from the Web, standardize it and publish it through a digital library system. It provides support to services and organizational structure normally available in digital libraries, but benefiting from the breadth of the Web contents. We experimented with applying the Web-DL environment to the Networked Digital Library of Theses and Dissertations (NDLTD), thus demonstrating that the rapid construction of DLs from the Web is possible. Also, Web-DL provides an alternative as a large-scale solution for interoperability between independent digital libraries.} } @INPROCEEDINGS{Newby03 ,AUTHOR = "Gregory B. Newby and Charles Franks" ,TITLE = "Distributed Proofreading [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {Distributed proofreading allows many people working individually across the Internet to contribute to the proofreading of a new electronic book. This paper describes Project Gutenberg's Distributed Proofreading project, along with our general procedures for creating an electronic book from a physical book. Distributed proofreading has promise for the future of Project Gutenberg, and is likely to be a useful strategy for other digital library projects.} } @INPROCEEDINGS{Droettboom03 ,AUTHOR = "Michael Droettboom " ,TITLE = "Correcting broken characters in the recognition of historical printed documents [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {This paper presents a new technique for dealing with broken characters, one of the major challenges in the optical character recognition (OCR) of degraded historical printed documents. A technique based on graph combinatorics is used to rejoin the appropriate connected components. It has been applied to real data with successful results.} } @INPROCEEDINGS{Brown03 ,AUTHOR = " Michael S. Brown and Desmond Tsoi" ,TITLE = "Correcting Common Image Distortions in Library Materials Acquired by a Camera [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {We present a technique to correct image distortion that can occur when library materials are imaged by cameras. Our approach provides a general framework to undo a variety of common distortions, including binder curl, fold distortion, and combinations of the two. Our algorithm is described and demonstrated on several examples.} } @INPROCEEDINGS{Efron03 ,AUTHOR = "Miles Efron and Donald Sizemore " ,TITLE = "Link Attachment (Preferential and Otherwise) in Contributor-Run Digital Libraries [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {Ibiblio is a digital library whose materials are submitted and maintained by volunteer contributors. This study analyzes the emergence of hyperlinked structures within the ibiblio collection. In the context of ibiblio, we analyze the suitability of Barabasi's model of preferential attachment to describe the distribution of incoming links. We find that the degree of maintainer activity for a given site (as measured by the voluntary development of descriptive metadata) is a stronger link count predictor for ibiblio than is a site's age, as the standard model predicts. Thus we argue that the efforts of ibiblio's contributors positively affect the popularity of their materials.} } @INPROCEEDINGS{Rydberg03 ,AUTHOR = " Jeffrey A. Rydberg-Cox" ,TITLE = "Automatic Disambiguation of Latin Abbreviations in Early Modern Texts for Humanities Digital Libraries [short paper]" ,BOOKTITLE = jcdl03 ,YEAR = "2003" ,entered-by = "Rebecca Wesley" ,abstract = {Early modern books written in Latin contain many abbreviations of common words that are derived from earlier manuscript practice. While these abbreviations are usually easily deciphered by a reader well-versed in Latin, they pose technical problems for full text digitization: they are difficult to OCR or have typed and - if they are not expanded correctly - they limit the effectiveness of information retrieval and reading support tools in the digital library. In this paper, I will describe a method for the automatic expansion and disambiguation of these abbreviations.} } @TECHREPORT{paep03 ,AUTHOR = "Andreas Paepcke and QianYing Wang and Sheila Patel and Matthew Wang and Harada Susumu" ,TITLE = "A Cost-Effective Three-in-One PDA Input Control" ,INSTITUTION = "Stanford University" ,YEAR = "2003" ,month = "August" ,number = "2003-60" ,note = "Available at http://dbpubs.stanford.edu/pub/2003-60" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2003-60)" ,entered-by = "Andreas Paepcke" ,status = "Submitted for Publication" ,keywords = "tactile, haptic, pressure sensor, FSR, PDA input" ,abstract = {We attach an inexpensive pressure sensor to the side of a PDA and use it as three input devices at once. Users can squeeze the device to provide near-continuous input to applications. At the same time the drivers interpret a sudden full squeeze as the push of a virtual button. A user's sudden pressure release while squeezing is detected as the push of a second virtual button. We briefly describe our hardware and signal processing techniques. The remainder of the writing describes an experiment that explores whether users can cope cognitively with the 3-in-1 control. We compare against a three-control setup consisting of a jog wheel and two physical buttons. We show that the 3-in-1 control enables a 13% faster reaction time over the three-control, but that the 3-in-1 suffers a 4% penalty in the accuracy of users choosing between the two buttons in response to cues from an application. We show that a good choice of application cue is more important for assuring accuracy in the 3-in-1 than in the more traditional set of separate controls. In particular, we examined four types of cues. One abstract cue, one cue with clear semantic relevance to the application, one symbolic, and one textual cue. } } @INPROCEEDINGS{Cars99 ,AUTHOR = "Chad Carson and Megan Thomas and Serge Belongie and Joseph M. Hellerstein and Jitendra Malik" ,TITLE = "Blobworld: A system for Region-Based Image Indexing and Retrieval" ,BOOKTITLE = "Proceedings of the Third International Conference on Visual Information Systems" ,YEAR = "1999" ,month = "June" ,entered-by = "Mor Naaman" } @INPROCEEDINGS{Barn01 ,AUTHOR = "Kobus Barnard and David .A. Forsyth" ,TITLE = "Learning the Semantics of Words and Pictures" ,BOOKTITLE = "Proceedings of the IEEE International Conference on Computer Vision" ,YEAR = "2001" ,month = "July" ,entered-by = "Mor Naaman" } @INPROCEEDINGS{wuma97 ,author = "Victor Wu and R. Manmatha and Edward M. Riseman" ,title = "Finding Text in Images" ,booktitle = dl97 ,year = "1997" ,entered-by = "Mor Naaman" } @INPROCEEDINGS{Froh02 ,author = {David Frohlich and Allan Kuchinsky and Celine Pering and Abbe Don and Steven Ariss} ,title = {Requirements for Photoware} ,booktitle = {Proceedings of the 2002 ACM conference on Computer supported cooperative work} ,year = {2002} ,location = {New Orleans, Louisiana, USA} ,entered-by = "Mor Naaman" } @TECHREPORT{Kule03 ,AUTHOR = "Bill Kules and Hyunmo Kang and Catherine Plaisant and Anne Rose and Ben Shneiderman" ,TITLE = "Immediate Usability: Kiosk Design Principles From The {CHI} 2001 Photo Library" ,INSTITUTION = "University of Maryland" ,YEAR = "2003" ,number = "CS-TR-4293" ,links = "(title:www:http://www.cs.umd.edu/Library/TRs/)" ,entered-by = "Mor Naaman" } @article{Jain99, author = {A. K. Jain and M. N. Murty and P. J. Flynn}, title = {Data Clustering: a Review}, journal = csurvey, volume = {31}, number = {3}, year = {1999}, issn = {0360-0300}, pages = {264--323}, links = "(title:www:http://doi.acm.org/10.1145/331499.331504)", publisher = {ACM Press}, entered-by = "Mor Naaman" } @ARTICLE{Hill99 ,AUTHOR = "Linda L. Hill and James Frew and Qi Zheng" ,TITLE = "Geographic Names - The Implementation of a Gazetteer in a Georeferenced Digital Library" ,JOURNAL = "CNRI D-Lib Magazine" ,YEAR = "1999" ,month = "January" ,links = "title:www:http://www.dlib.org/dlib/january99/hill/01hill.html" ,entered-by = "Mor Naaman" } @TECHREPORT{Velt02 ,AUTHOR = "Remco C. Veltkamp and Mirela Tanase" ,TITLE = "Content-Based Image Retrieval Systems: A Survey" ,INSTITUTION = "Department of Computing Science, Utrecht University" ,YEAR = "2002" ,MONTH = "October" ,number = "TR UU-CS-2000-34 (revised version)" ,links = "(title:www:http://give-lab.cs.uu.nl/cbirsurvey/)" ,entered-by = "Mor Naaman" ,abstract = {~} } @INPROCEEDINGS{Shne00 ,AUTHOR = "Ben Shneiderman and Hyunmo Kang" ,TITLE = "Direct Annotation: A Drag-and-Drop Strategy for Labeling Photos" ,booktitle = {Proceedings of the International Conference on Information Visualization} ,year = "2000" ,month = "May" ,location = {London, England} } @INPROCEEDINGS{Weny01 ,AUTHOR = "Liu Wenyin and Susan Dumais and Yanfeng Sun and HongJiang Zhang and Mary Czerwinski and Brent Field" ,title = {Semi-automatic Image Annotation} ,booktitle = {8th International Conference on Human-Computer Interactions (INTERACT 2001)} ,location = "Tokyo, Japan" ,year = 2001 ,month = "July" ,entered-by = "Mor Naaman" } @INPROCEEDINGS{Kuch99, author = {Allan Kuchinsky and Celine Pering and Michael L. Creech and Dennis Freeze and Bill Serra and Jacek Gwizdka}, title = {FotoFile: a Consumer Multimedia Organization and Retrieval System}, booktitle = chi99, year = {1999}, isbn = {0-201-48559-1}, pages = {496--503}, location = {Pittsburgh, Pennsylvania, United States}, entered-by = "Mor Naaman" } @TECHREPORT{naam02 ,AUTHOR = "Mor Naaman and Hector Garcia-Molina and Andreas Paepcke" ,TITLE = "Evaluation of Delivery Techniques for Dynamic Web Content (Extended Version)" ,INSTITUTION = "Stanford University" ,YEAR = "2002" ,month = "June" ,note = "Available at http://dbpubs.stanford.edu/pub/2002-31" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2002-31)" ,entered-by = "Mor Naaman" } @inproceedings{Naam03, author = "Mor Naaman and Hector Garcia-Molina and Andreas Paepcke", title = "Evaluation of ESI and Class-Based Delta Encoding", booktitle = {8th International Workshop on Web Content Caching and Distribution (IWCW 2003)}, year = {2003}, note = "Available at http://dbpubs.stanford.edu/pub/2003-61", links = "(title:www:http://dbpubs.stanford.edu/pub/2003-61)", entered-by = "Mor Naaman" } @article{hunt98 ,title = "Delta Algorithms: An Empirical Analysis" ,author = "James J. Hunt and Kiem-Phong Vo and Walter F. Tichy" ,journal = "ACM Transactions on Software Engineering and Methodology" ,volume = 7 ,pages = "192-214" ,year = "1998" } @inproceedings{korn02 ,author = "David G. Korn and Kiem-Phong Vo" ,title = "Engineering a Differencing and Compression Data Format" ,booktitle = "Proceedings of Usenix 2002" ,publisher = "USENIX" ,year = 2002 } @Misc{PPal, key = {PhotoPals}, title = {PhotoPals Photo Album}, howpublished = {http://photopals2002.com}, links = {title:www:http://photopals2002.com}, entered-by = {Mor Naaman} } @Misc{RPic, key = {Resco Picture Viewer}, title = {Resco Picture Viewer for Pocket PC}, howpublished = {http://www.resco-net.com/}, links = {title:www:http://www.resco-net.com}, entered-by = {Mor Naaman} } @Misc{Handa, key = {Handango}, title = {Handango, Inc}, howpublished = {http://www.handango.com}, links = {title:www:http://www.handango.com}, entered-by = {Mor Naaman} } @inproceedings{Bede01, author = {Benjamin B. Bederson}, title = {PhotoMesa: a zoomable image browser using quantum treemaps and bubblemaps}, booktitle = {Proceedings of the 14th annual ACM symposium on User interface software and technology}, year = {2001}, isbn = {1-58113-438-X}, pages = {71--80}, location = {Orlando, Florida}, doi = {http://doi.acm.org/10.1145/502348.502359}, publisher = {ACM Press}, entered-by = "Mor Naaman" } @article{Wage86, author = {Wagenaar, W.A.}, title = {My memory: A study of autobiographical memory over six years}, journal = {Cognitive psychology}, volume = {18}, year = {1986}, pages = {225--252}, entered-by = "Mor Naaman" } @INPROCEEDINGS{Kang00, author = {Hyunmo Kang and Ben Shneiderman}, title = {Visualization Methods for Personal Photo Collections: Browsing and Searching in the PhotoFinder}, booktitle = {IEEE International Conference on Multimedia and Expo}, year = {2000}, location = {New York, New York, United States}, entered-by = "Mor Naaman" } @TECHREPORT{Garg03 ,AUTHOR = "Ullas Gargi" ,TITLE = "Consumer Media Capture: Time-Based Analysis and Event Clustering" ,INSTITUTION = "HP Laboratories" ,YEAR = "2003" ,MONTH = "August" ,number = "HPL-2003-165" ,links = "(title:www:http://www.hpl.hp.com/techreports/2003/HPL-2003-165.pdf)" ,entered-by = "Mor Naaman" ,abstract = {~} } @INPROCEEDINGS{Loui00, author = {A. Loui and A. E. Savakis}, title = {Automatic Image Event Segmentation and Quality Screening for Albuming Applications}, booktitle = {IEEE International Conference on Multimedia and Expo}, year = {2000}, location = {New York, New York, United States}, entered-by = "Mor Naaman" } @inproceedings{Loui01, author = {Amanda Stent and Alexander Loui}, title = {Using event segmentation to improve indexing of consumer photographs}, booktitle = {24th annual international ACM SIGIR conference on Research and development in information retrieval}, year = {2001}, isbn = {1-58113-331-6}, pages = {59--65}, location = {New Orleans, Louisiana, United States}, doi = {http://doi.acm.org/10.1145/383952.383960}, publisher = {ACM Press}, entered-by = "Mor Naaman" } @article{Shen03, author = {Chia Shen and Neal Lesh and Frdric Vernier}, title = {Personal digital historian: story sharing around the table}, journal = {interactions}, volume = {10}, number = {2}, year = {2003}, issn = {1072-5520}, pages = {15--22}, doi = {http://doi.acm.org/10.1145/637848.637856}, publisher = {ACM Press}, entered-by = "Mor Naaman" } @TECHREPORT{Plat02 ,AUTHOR = "John C. Platt and Mary Czerwinski and Brent A. Field" ,TITLE = "PhotoTOC: Automatic Clustering for Browsing Personal Photographs" ,INSTITUTION = "Microsoft Research" ,YEAR = "2002" ,MONTH = "February" ,number = "MSR-TR-2002-17" ,links = "(title:www:ftp://ftp.research.microsoft.com/pub/tr/tr-2002-17.pdf)" ,entered-by = "Mor Naaman" ,abstract = {~} } @INPROCEEDINGS{Naam03a, author = {Mor Naaman and Andreas Paepcke and Hector Garcia-Molina}, title = {From Where to What: Metadata Sharing for Digital Photographs with Geographic Coordinates}, booktitle = "10th International Conference on Cooperative Information Systems (CoopIS)", year = {2003}, location = {Catania, Sicily, Italy}, comment = "Available at http://dbpubs.stanford.edu/pub/2003-37.", links = "(title:www:http://dbpubs.stanford.edu/pub/2003-37)", entered-by = "Mor Naaman" } @INPROCEEDINGS{Toya03, author = {Kentaro Toyama and Ron Logan and Asta Roseway}, title = {Geographic location tags on digital images}, booktitle = mm03, year = {2003}, isbn = {1-58113-722-2}, pages = {156--166}, location = {Berkeley, CA, USA}, doi = {http://doi.acm.org/10.1145/957013.957046}, publisher = {ACM Press}, entered-by = "Mor Naaman" } @inproceedings{Aris03, author = {Aristides Gionis and Heikki Mannila}, title = {Finding recurrent sources in sequences}, booktitle = {Proceedings of the seventh annual international conference on Computational molecular biology}, year = {2003}, isbn = {1-58113-635-8}, pages = {123--130}, location = {Berlin, Germany}, doi = {http://doi.acm.org/10.1145/640075.640091}, publisher = {ACM Press}, entered-by = "Mor Naaman" } @article{Schw78, author = {Gideon Schwarz}, title = {Estimating the dimension of a model}, journal = {The Annals of Statistic}, volume = {6}, year = {1978}, pages = {461--464}, entered-by = "Mor Naaman" } @inproceedings{Jone02, author = {Christopher B. Jones and R. Purves and A. Ruas and M. Sanderson and M. Sester and M. {van Kreveld} and R. Weibel}, title = {Spatial information retrieval and geographical ontologies an overview of the SPIRIT project}, booktitle = {Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval}, year = {2002}, isbn = {1-58113-561-0}, pages = {387--388}, location = {Tampere, Finland}, doi = {http://doi.acm.org/10.1145/564376.564457}, publisher = {ACM Press}, entered-by = "Mor Naaman" } @article{Spin03, author = {Diomidis Spinellis}, title = {Position-annotated photographs: A geotemporal web}, journal = {IEEE Pervasive Computing}, volume = {2}, number = {2}, year = {2003}, pages = {72--79}, publisher = {IEEE}, entered-by = "Mor Naaman" } @inproceedings{Coop03, author = {Matthew Cooper and Jonathan Foote and Andreas Girgensohn and Lynn Wilcox}, title = {Temporal event clustering for digital photo collections}, booktitle = {Proceedings of the eleventh ACM international conference on Multimedia}, year = {2003}, isbn = {1-58113-722-2}, pages = {364--373}, location = {Berkeley, CA, USA}, doi = {http://doi.acm.org/10.1145/957013.957093}, publisher = {ACM Press}, entered-by = "Mor Naaman" } @article{Beef99, author = "Doug Beeferman and Adam Berger and John D. Lafferty", title = "Statistical Models for Text Segmentation", journal = "Machine Learning", volume = "34", number = "1-3", pages = "177--210", year = "1999", entered-by = "Mor Naaman" } @article{Pevz02, author = {Lev Pevzner and Marti Hearst}, title = {A Critique and Improvement of an Evaluation Metric for Text Segmentation}, journal = {Computational Linguistics}, volume = {28}, number = {1}, year = {2002}, pages = {19--36}, entered-by = "Mor Naaman" } @inproceedings{Keog01, author = "Eamonn J. Keogh and Selina Chu and David Hart and Michael J. Pazzani", title = "An Online Algorithm for Segmenting Time Series", pages = "289-296", year = "2001", booktitle = {IEEE International Conference on Data Mining}, isbn = {0769511198}, location = {San Jose, CA, USA}, entered-by = "Mor Naaman" } @inproceedings{Psou02, author = "Konstantinos Psounis", title = "Class-based delta-encoding: a scalable scheme for caching dynamic Web content", booktitle = {22nd International Conference on Distributed Computing Systems Workshops}, year = {2002}, location = {Vienna, Austria}, entered-by = "Mor Naaman" } @inproceedings{chal00 ,author = "Jim Challenger and Arun Iyengar and Karen Witting and Cameron Ferstat and Paul Reed" ,title = "A publishing system for Efficiently Creating Dynamic Web Content" ,booktitle = "Proceedings of IEEE INFOCOM 2000, Tel Aviv, Israel" ,year = "2000" ,entered-by = "Mor Naaman" } @INPROCEEDINGS{cao98 ,AUTHOR = "Pei Cao and Jin Zhang and Kevin Beach" ,TITLE = "Active Cache: Caching Dynamic Contents on the Web" ,BOOKTITLE = "Proceedings of IFIP International Conference on Distributed Systems Platforms and Open Distributed Processing (Middleware '98)" ,YEAR = "1998" ,pages = "373---388" ,entered-by = "Mor Naaman" } @Misc{ESI ,title = "{ESI} 1.0" ,howPublished = {http://www.w3.org/TR/esi-lang} ,links = "(title:www:http://www.w3.org/TR/esi-lang)" ,entered-by = {Mor Naaman} } @inproceedings{doug97 ,author = "Fred Douglis and Antonio Haro and Michael Rabinovich" ,title = "HPP: HTML Macro-Preprocessing to Support Dynamic Document Caching" ,booktitle = "Proceedings of the USENIX Symposium on Internet Technologies and Systems, Monterey, California" ,year = "1997" ,entered-by = "Mor Naaman" } @article{Road00, author = {Chris Roadknight and Ian Marshall and Debbie Vearer}, title = {File popularity characterisation}, journal = {SIGMETRICS Perform. Eval. Rev.}, volume = {27}, number = {4}, year = {2000}, issn = {0163-5999}, pages = {45--50}, doi = {http://doi.acm.org/10.1145/346000.346014}, publisher = {ACM Press}, entered-by = "Mor Naaman" } @inproceedings{mogu97 ,author = "Jeffrey C. Mogul and Fred Douglis and Anja Feldmann and Balachander Krishnamurthy" ,title = "Potential Benefits of Delta Encoding and Data Compression for HTTP" ,booktitle = "Proceedings of ACM SIGCOMM" ,pages = "181-194" ,year = "1997" ,entered-by = "Mor Naaman" ,note = "An extended version appears as Research Report 97/4, Digital Equipment Corporation Western Research Laboratory July, 1997" } @Misc{fgwp ,author = "" ,title = "{FineGround Networks. Breaking} New Ground in Content Acceleration" ,howPublished = "http://www.fineground.com/pdf/FGCWhitepaper.pdf" ,links = "(title:www:http://www.fineground.com/pdf/FGCWhitepaper.pdf)" ,entered-by = "Mor Naaman" } @inproceedings{Bang97 ,author = "Gaurav Banga and Fred Douglis and Michael Rabinovich" ,title = "Optimistic Deltas for WWW Latency Reduction" ,booktitle = "Proceedings of USENIX Technical Conference" ,pages = "289--303" ,year = "1997" ,location = {Anaheim, CA, USA} ,entered-by = "Mor Naaman" } @inproceedings{hous96 ,author="B.C. Housel and D.B. Lindquist" ,title="WebExpress: A System for Optimizing Web Browsing in a Wireless Environment" ,booktitle = "In Proceedings of the Second Annual International Conference on Mobile Computing and Networking, pages 108--116, November 1996" ,year="1996" ,entered-by = "Mor Naaman" } @inproceedings{wolm99 ,author=" Alec Wolman and Geoffrey M. Voelker and Nitin Sharma and Neal Cardwell and Anna Karlin and and Henry M. Levy " ,title=" On the scale and performance of cooperative Web proxy caching" ,booktitle = "Proceedings of the 17th ACM symposium on Operating Systems Principles (SOSP 99)" ,note = "Published as Operating Systems Review 34(5):16-31, December 1999" ,year="1999" ,entered-by = "Mor Naaman" } @inproceedings{Rabi03 ,author="Michael Rabinovich and Zhen Xiao and Fred Douglis and Chuck Kalmanek" ,title="Moving Edge-Side Includes to the Real Edge - the Clients" ,booktitle = "USENIX Symposium on Internet Technologies and Systems" ,year="2003" ,entered-by = "Mor Naaman" } @inproceedings{chal99 ,author = "Jim Challenger and Paul Dantzig and Arun Iyengar" ,title = "A Scalable System for Consistently Caching Dynamic Web Data" ,booktitle = "Proceedings of the 18th Annual Joint Conference of the {IEEE} Computer and Communications Societies" ,address = "New York, New York" ,year = "1999", } @ARTICLE{zipf29 ,AUTHOR = "George Kingsley Zipf" ,TITLE = "Relative frequency as a determinant of phonetic change" ,JOURNAL = "Reprinted from the Harvard Studies in Classical Philology" ,YEAR = "1929" ,volume = "XL" ,entered-by = "Mor Naaman" } @inproceedings{alme96 ,author="Virgilio Almeida and Azer Bestavros and Mark Crovella and Adriana de Oliveira" ,title="Characterizing Reference Locality in the WWW" ,booktitle = "Proceedings of PDIS'96: The IEEE Conference on Parallel and Distributed Information Systems" ,year="1996" ,entered-by = "Mor Naaman" } @inproceedings{glas94 ,author = "Steven Glassman" ,title = "A caching relay for the world wide web" ,booktitle = "Proceedings of the First International World-Wide Web Conference" ,year = "1994" ,entered-by = "Mor Naaman" } @INPROCEEDINGS{bres99 ,AUTHOR = "Lee Breslau and Pei Cao and Li Fan and Graham Phillips and Scott Shenker" ,TITLE = "Web Caching and Zipf-like Distributions: Evidence and Implications" ,BOOKTITLE = "Proceedings of Infocom" ,YEAR = "1999" ,entered-by = "Mor Naaman" } @inproceedings{padm00 ,author = "V. N. Padmanabhan and L. Qiu" ,title = "The Content and Access Dynamics of a Busy Web Site: Findings and Implications" ,booktitle = "Proceedings of ACM SIGCOMM, Stockholm, Sweden" ,year = "2000" ,entered-by = "Mor Naaman" } @TECHREPORT{naa03 ,AUTHOR = "Mor Naaman and Hector Garcia-Molina and Andreas Paepcke" ,TITLE = "Evaluation of Delivery Techniques for Dynamic Web Content" ,INSTITUTION = "Stanford University" ,YEAR = "2003" ,number = "2003-7" ,links = "(title:www:http://dbpubs.stanford.edu/pub/2003-7)" ,note = "Available at http://dbpubs.stanford.edu/pub/2003-7" ,entered-by = "Andreas Paepcke" } @INPROCEEDINGS{naa04a ,AUTHOR = "Mor Naaman and Yee Jiun Song and Andreas Paepcke and Hector Garcia-Molina" ,TITLE = "Automatically Generating Metadata for Digital Photographs with Geographic Coordinates" ,BOOKTITLE = www04 ,YEAR = "2004" ,entered-by = "Mor Naaman" } @BOOK{Long01 ,AUTHOR = "Paul Longley and Michael Goodchild and David Maguire and David Rhind" ,TITLE = "Geographic Information Systems and Science" ,PUBLISHER = "John Wiley \& Sons" ,YEAR = "2001" ,entered-by = "Susumu Harada" } @INPROCEEDINGS{Lieb02, title = {Adaptive linking between text and photos using common sense reasoning.}, author = {H. Lieberman and Hugo Liu}, pages = {2 -- 11}, year = {2002}, booktitle = {Adaptive Hypermedia and Adaptive Web-Based Systems. Second International Conference, AH 2002. Proceedings, 29-31 May 2002, Malaga, Spain}, publisher = {Springer-Verlag, 2002}, copyright = {(c)2004 IEE}, entered-by = "Susumu Harada" } @INPROCEEDINGS{Cave01 ,AUTHOR = "Duncan Cavens and Stephen Sheppard and Michael Meitner" ,TITLE = "Image Database Extension to ArcView: How to Find the Photograph You Want" ,BOOKTITLE = "Proceedings of ESRI Users Conference" ,YEAR = "2001" ,LOCATION = {San Diego, CA, USA} ,entered-by = "Susumu Harada" } @INPROCEEDINGS{Plai96, author = {Brett Milash and Catherine Plaisant and Anne Rose}, title = {LifeLines: visualizing personal histories}, booktitle = {Conference companion on Human factors in computing systems}, year = {1996}, isbn = {0-89791-832-0}, pages = {392--393}, location = {Vancouver, British Columbia, Canada}, doi = {http://doi.acm.org/10.1145/257089.257391}, publisher = {ACM Press}, } @TECHREPORT{Kang04 ,AUTHOR = "Hyunmo Kang and Ben Shneiderman" ,TITLE = "Exploring Personal Media: A Spatial Interface Supporting User-defined Semantic Regions" ,YEAR = "2005" ,INSTITUTION = "University of Maryland" ,number = "ISR 2005-51" ,links = "(title:www:http://techreports.isr.umd.edu/reports/2005/TR_2005-51.pdf)" ,abstract = "Media Finder" ,entered-by = "Susumu Harada, Mor Naaman" } @article{Smith96-2, title = {A digital library for geographically referenced materials}, author = {Terence R. Smith}, journal = {Computer}, volume = {29}, number = {5}, pages = {54 -- 60}, month = {MAY}, year = {1996}, publisher = {IEEE Comput. Soc, 1996}, entered-by = "Mor Naaman" } @INPROCEEDINGS{Lecl01 ,AUTHOR = "Yvan Leclerc and Martin Reddy and Lee Iverson and Michael Eriksen" ,TITLE = "The GeoWeb - A New Paradigm for Finding Data on the Web" ,booktitle = "International Cartographic Conference ({ICC}2001)" ,location = {Beijing, China} ,YEAR = "2001" ,entered-by = "Susumu Harada" } @article{bush45 ,AUTHOR = "Vannevar Bush" ,TITLE = "As We May Think" ,JOURNAL = "The Atlantic Monthly" ,YEAR = "1945" ,MONTH = "July" ,LINKS = "(title:www:http://www.theatlantic.com/unbound/flashbks/computer/bushf.htm)" ,COMMENT = "Available at http://www.theatlantic.com/unbound/flashbks/computer/bushf.htm" ,entered-by = "Mor Naaman" } @TECHREPORT{naa04b ,AUTHOR = "Mor Naaman and Susumu Harada and QianYing Wang and Andreas Paepcke" ,TITLE = "Adventures in Space and Time: Browsing Personal Collections of Geo-Referenced Digital Photographs" ,INSTITUTION = "Stanford University" ,YEAR = "2004" ,month = "April" ,LINKS = "(title:www:http://dbpubs.stanford.edu/pub/2004-26)" ,note = "Available at http://dbpubs.stanford.edu/pub/2004-26" ,entered-by = "Mor Naaman" } @INPROCEEDINGS{Kumar04 ,AUTHOR = "Anoop Kumar and Ranjani Saigal and Robert Chavez and Nikolai Schwertner" ,TITLE = "Architecting an Extensible Digital Repository" ,BOOKTITLE = jcdl04 ,YEAR = "2004" ,entered-by = "Rebecca Wesley" ,abstract = {The Digital Collection and Archives (DCA) in partnership with Academic Technology (AT) at Tufts University developed a digital library solution for long-term storage and integration of existing digital collections, like Perseus, TUSK, Bolles and Artifact. In this paper, we describe the Tufts Digital Library (TDL) architecture. TDL is an extensible, modular, flexible and scalable architecture that uses FEDORA at its core. The extensible nature of the TDL architecture allows for seamless integration of collections that may be developed in the future, while leveraging the extensive tools that are available as part of individual digital library applications at Tufts. We describe the functionality and implementation details of the individual components of TDL. Two applications that have successfully interfaced with TDL are presented. We conclude with some remarks about the future development of TDL. } } @INPROCEEDINGS{Jerez04 ,AUTHOR = "Henry N. Jerez and Xiaoming Liu and Patrick Hochstenbach and Herbert Van de Sompel" ,TITLE = "The multi-faceted use of the OAI-PMH in the LANL Repository" ,BOOKTITLE = jcdl04 ,YEAR = "2004" ,entered-by = "Rebecca Wesley" ,abstract = {This paper focuses on the multifaceted use of the OAI-PMH in a repository architecture designed to store digital assets at the Research Library of the Los Alamos National Laboratory (LANL), and to make the stored assets available in a uniform way to various downstream applications. In the architecture, the MPEG-21 Digital Item Declaration Language is used as the XML-based format to represent complex digital objects. Upon ingestion, these objects are stored in a multitude of autonomous OAI-PMH repositories. An OAI-PMH compliant Repository Index keeps track of the creation and location of all those repositories, whereas an Identifier Resolver keeps track of the location of individual objects. An OAI-PMH Federator is introduced as a single-point-of-access to downstream harvesters. It hides the complexity of the environment to those harvesters, and allows them to obtain transformations of stored objects. While the proposed architecture is described in the context of the LANL library, the paper will also touch on its more general applicability. } } @INPROCEEDINGS{Borbinha04 ,AUTHOR = "Jos Borbinha and Nuno Freire and Joo Neves" ,TITLE = "BND: A National Digital Library as a jigsaw" ,BOOKTITLE = jcdl04 ,YEAR = "2004" ,entered-by = "Rebecca Wesley" ,abstract = {This paper describes the architecture and components of the infrastructure in construction for the National Digital Library in Portugal. The requirements emerged from the definition of the services to support, with a special focus on scalability, and from the decision to give a special attention to community building standards, open solutions, and reusable and cost effective components. The generic bibliographic metadata format in this project is UNIMARC, and the structural metadata is METS. The URN identifiers are processed and resolved as simple but very effective PURL identifiers, and the storage is provided by the new emerging LUSTRE file system, for immediate access, and by a locally developed GRID architecture, ARCO, for long term preservation. All these components run on Linux servers, as also the middleware for access based in the FEDORA framework. } } @INPROCEEDINGS{Laender04 ,AUTHOR = "Alberto H. F. Laender and Marcos Andr Gonalves and Pablo A. Roberto" ,TITLE = "BDBComp: Building a Digital Library for the Brazilian Computer Science Community" ,BOOKTITLE = jcdl04 ,YEAR = "2004" ,entered-by = "Rebecca Wesley" ,abstract = {This paper reports initial efforts towards building BDBComp, a digital library for the Brazilian computer science community. BDBComp is based on a number of standards (e.g., OAI, Dublin Core, SQL) as well as on new technologies (e.g., Web data extraction tools), which allowed fast and easy prototyping. The paper focuses on architectural issues and specific challenges faced during the construction of this digital library as well as on proposed solutions. } } @INPROCEEDINGS{FuYa04 ,AUTHOR = "Yueyu Fu and Javed Mostafa" ,TITLE = "Integration of Biomedical Text and Sequence OAI Repositories" ,BOOKTITLE = jcdl04 ,YEAR = "2004" ,entered-by = "Rebecca Wesley" ,abstract = {Archived biomedical literature and sequence data are growing rapidly. OAI-PMH provides a convenient way for data sharing, but it has not been tested in the biomedical domain, especially in dealing with different types of data, such as protein, and gene sequences. We built four individual OAI-PMH repositories based on different biomedical resources. Using the harvested data from the four repositories we created an integrated OAI-PMH repository, which hosts the linked literature and sequence data in a single place. } } @INPROCEEDINGS{Blandford04 ,AUTHOR = "Ann Blandford and Suzette Keith and Iain Connell and Helen Edwards" ,TITLE = "Analytical usability evaluation for Digital Libraries: a case study" ,BOOKTITLE = jcdl04 ,YEAR = "2004" ,entered-by = "Rebecca Wesley" ,abstract = {There are two main kinds of approach to considering usability of any system: empirical and analytical. Empirical techniques involve testing systems with users, whereas analytical techniques involve usability personnel assessing systems using established theories and methods. We report here on a set of studies in which four different techniques were applied to various digital libraries, focusing on the strengths, limitations and scope of each approach. Two of the techniques, Heuristic Evaluation and Cognitive Walkthrough, were applied in text-book fashion, because there was no obvious way to contextualize them to the Digital Libraries (DL) domain. For the third, Claims Analysis, it was possible to develop a set of re-usable scenarios and personas that relate the approach specifically to DL development. The fourth technique, CASSM, relates explicitly to the DL domain by combining empirical data with an analytical approach. We have found that Heuristic Evaluation and Cognitive Walkthrough only address superficial aspects of interface design (but are good for that), whereas Claims Analysis and CASSM can help identify deeper conceptual difficulties (but demand greater skill of the analyst). However, none fit seamlessly within the fragmented function-oriented design practices that typify much digital library development, highlighting an important area for further work to support improved usability.} } @INPROCEEDINGS{Champeny04 ,AUTHOR = "Leslie Champeny and Christine L. Borgman and Patricia Mautone and Richard E. Mayer and Richard A. Johnson and Gregory H. Leazer and Anne J. Gilliland-Swetland and Kelli A. Millwood and Leonard D'Avolio and Jason Finley and Laura J. Smart" ,TITLE = "Developing a Digital Learning Environment: an evaluation of design and implementation processes" ,BOOKTITLE = jcdl04 ,YEAR = "2004" ,entered-by = "Rebecca Wesley" ,abstract = {The Alexandria Digital Earth Prototype (ADEPT) Project (1999-2004) builds upon the Alexandria Digital Library Project (1994-99) to add functions and services for undergraduate teaching to a digital library of geospatial resources. The Digital Learning Environment (DLE) services are being developed and evaluated iteratively over the course of this research project. In the 2002-2003 academic year, the DLE was implemented in stages during the fall and spring terms in undergraduate geography courses at the University of California, Santa Barbara (UCSB). Evaluation of the fall term implementation identified design issues of time and complexity of use in the services for creating and organizing course domain knowledge. By the time of the spring term implementation, these issues were addressed and new services added for integrating selected course content into a variety of class presentation formats. The implementation was evaluated via interviews with the course instructor, development staff, and students, and by observations (in person and videotaped) of the course. Results of the iterative evaluation indicated that usability and functionality for the instructor had increased between the two course offerings. Students found classroom presentations to be useful for understanding concepts, and Web access to the presentations useful for study and review. Assessments of student learning suggest modest improvements over time. Developers are now applying lessons learned during these implementations to improve the system for subsequent implementation in the 2003-04 academic year. } } @INPROCEEDINGS{Cunningham04 ,AUTHOR = "Sally Jo Cunningham and David Bainbridge and Masood Masoodian" ,TITLE = "How People Describe Their Image Information Needs: A Grounded Theory Analysis of Visual Arts Queries" ,BOOKTITLE = jcdl04 ,YEAR = "2004" ,entered-by = "Rebecca Wesley" ,abstract = {When people are looking for visual arts information -- information related to images -- how do they characterize their needs? We analyze a set of 405 queries to identify the attributes that people provide to the Google Answers' "ask an expert" online reference system. The results suggest directions to take in developing an effective organization and features for an image digital library. } } @INPROCEEDINGS{Moraveji04 ,AUTHOR = "Neema Moraveji" ,TITLE = "Improving Video Browsing with an Eye-Tracking Evaluation of Feature-Based Color Bars" ,BOOKTITLE = jcdl04 ,YEAR = "2004" ,entered-by = "Rebecca Wesley" ,abstract = {This paper explains a method for leveraging the standard video timeline widget as an interactive visualization of image features. An eye-tracking experiment is described with results that indicate that such a widget increases task efficiency without increasing complexity while being easily learned by experiment participants. } } @INPROCEEDINGS{Toms04 ,AUTHOR = "Elaine G. Toms and Christine Dufour and Susan Hesemeier