Combining Multiple Sources of Evidenceto Enhance Web Search Performance
2
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
The Web is rich with various sources of information that go beyond the contents of documents, such as hyperlinks and manually classified directories of Web documents such as Yahoo. This research extends past fusion IR studies, which have repeatedly shown that combining multiple sources of evidence (i.e. fusion) can improve retrieval performance, by investigating the effects of combining three distinct retrieval approaches for Web IR: the text-based approach that leverages document texts, the link-based approach that leverages hyperlinks, and the classification-based approach that leverages Yahoo categories. Retrieval results of text-, link-, and classification-based methods were combined using variations of the linear combination formula to produce fusion results, which were compared to individual retrieval results using traditional retrieval evaluation metrics. Fusion results were also examined to ascertain the significance of overlap (i.e. the number of systems that retrieve a document) in fusion. The analysis of results suggests that the solution spaces of text-, link-, and classification-based retrieval methods are diverse enough for fusion to be beneficial while revealing important characteristics of the fusion environment, such as effects of system parameters and relationship between overlap, document ranking and relevance.
Abstract
The Web is rich with various sources of information that go beyond the contents of documents, such as hyperlinks and manually classified directories of Web documents such as Yahoo. This research extends past fusion IR studies, which have repeatedly shown that combining multiple sources of evidence (i.e. fusion) can improve retrieval performance, by investigating the effects of combining three distinct retrieval approaches for Web IR: the text-based approach that leverages document texts, the link-based approach that leverages hyperlinks, and the classification-based approach that leverages Yahoo categories. Retrieval results of text-, link-, and classification-based methods were combined using variations of the linear combination formula to produce fusion results, which were compared to individual retrieval results using traditional retrieval evaluation metrics. Fusion results were also examined to ascertain the significance of overlap (i.e. the number of systems that retrieve a document) in fusion. The analysis of results suggests that the solution spaces of text-, link-, and classification-based retrieval methods are diverse enough for fusion to be beneficial while revealing important characteristics of the fusion environment, such as effects of system parameters and relationship between overlap, document ranking and relevance.
참고문헌 (31)
- Bartell, Brian T., "Automatic combination of multiple ranked retrieval systems", Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval (1994)
- Belkin, Nicholas J., "The effect of multiple query representations on information retrieval system performance", Proceedings of ACM SIGIR Conference on Research and Development in Information Retrieval, pp.339~346 (1993)
- Bharat, Krishnaand M. R. Henzinger, "Improved Algorithms for Topic Distillation in Hyperlinked Environments", Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval, pp.104~111 (1998)
- Brin, Serge, "The anatomy of a large-scale hyper textual Web search engine", Computer networks and ISDN systems, 30(1), pp.107~117 (1998)
- Buckley, Chris, "The Third Text Rerieval Conference (TREC-3)", pp.1~19 (1995), U.S. Government Printing Office
- Buckley, Chris, "The Fifth Text REtrieval Conference (TREC-5)", pp.105~118 (1997), U.S. Government Printing Office
- Buckley, Chris, A., "The Fourth Text REtrieval Conference (TREC-4)", pp.25~48 (1996), U.S. Government Printing Office
- Chakrabarti, Soumen, "Automatic resource list compilation by analyzing hyperlink structure and associated text", Proceedings of the 7th International World Wide Web Conference (1998)
- Fishburn, Peter C., "Utility theory for decision making" (1970), John Wiley & Sons
- Fox, Edward A., "The Second Text Rerieval Conference (TREC-2)", pp.243~252 (1994), U.S. Government Printing Office
- Fox, Edward A., "The Third Text Rerieval Conference (TREC-3)", pp.105~108 (1995), U.S. Government Printing Office
- Frakes, Williams B., "Information retrieval: Data structures & algorithms" (1992), Prentice Hall
- Gurrin, Cathal, "TheNineth Text Rerieval Conference(TREC-9)" (2001), U.S. Government Printing Office
- Katzer, Jeffrey, "A study of the overlap among document representations", Information Technology: Research and Development, 1, pp.261~274 (1982)
- Keen, E. Michael., "The Aberystwyth index languages test", Journal of Documentation, 29, pp.1~35 (1973)
- Kleinberg, Jon, "Authoritative sources in a hyperlinked environment", Journal of the Association for Computing Machinery, 46(5), pp.604~632 (1999)
- Combining multiple evidence from different relevance feedback methods(Tech. Rep. No.IR-87), "Lee, Joon Ho", University of Massachusetts, Center for Intelligent Information Retrieval, ~ (1996)
- Lee, Joon Ho., "Analyses of multiple evidence combination", Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval, pp.267~276 (1997)
- Modha, Dharmendra, "Clustering hypertext with applications to Web searching", Proceedings of the 11th ACM Hypertext Conference, pp.143~152 (2000)
- The Page Rank citation ranking: Bringing order to the Web, "Page, Larry", Stanford Digital Library Technologies Project, ~ (1998)
- Plaunt, Christian, "An Association Based Method for Automatic Indexing with a Controlled Vocabulary", Journal of the American Society for Information Science, 49(10), pp.888~902 (1998)
- Saracevic, Tefko, "A study of information seeking and retrieving. III. Searchers, searches, overlap", Journal of American Society for Information Science, 39, pp.197~216 (1988)
- Singhal, Amit, "Pivoted document length normalization", Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval, pp.21~29 (1996)
- Smith, Linda. C., "Selected Artificial Intelligence Techniques in Information Retrieval Systems Research", 박사, pp.1979
- Sparck Jones, Karen, "Automatic indexing", Journal of Documentation, 30, pp.393~432 (1974)
- Sumner, Robert. G., "The Sixth Text REtrieval Conference(TREC-6)" (1998)
- Vogt, Christopher. C, "Predicting the performance of linearly combined IR systems", Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval, pp.190~196 (1998)
- Williams, Martha E., "Analysis of terminology in various CAS data files as access points for retrieval", Journal of Chemical Information and Computer Sciences, 17, pp.16~20 (1977)
- Wong, S. K. Michael, "Linear structure in information retrieval", Proceedings of the 11th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp.219~232 (1988)
- Wong, S. K. Michael, "Evaluation of an adaptive linear model", Journal of the American Society for Information Science, 42, pp.723~730 (1991)
- Yang, Kiduk, "Information retrieval on the web", ARIST, 39(1), pp.33~80 (2005)