ABSTRACT
To facilitate the search for relevant information across a setof online distributed collections, a federated information retrieval system typically represents each collection, centrally, by a set of vocabularies or sampled documents. Accurate retrieval is therefore related to how precise each representation reflects the underlying content stored in that collection. As collections evolve over time, collection representations should also be updated to reflect any change, however, a current solution has not yet been proposed. In this study we examine both the implications of out-of-date representation sets on retrieval accuracy, as well as proposing three different policies for managing necessary updates. Each policyis evaluated on a testbed of forty-four dynamic collections over an eight-week period. Our findings show that out-of-date representations significantly degrade performance overtime, however, adopting a suitable update policy can minimise this problem.
- Avrahami, T., Yau, L., Si, L., and Callan, J. (2006). The FedLemur:federated search in the real world. Journal of the American Society for Information Science and Technology 57(3):347--358. Google ScholarDigital Library
- Baillie, M., Azzopardi, L., and Crestani, F. (2006). Adaptive query-based sampling of distributed collections. In Proc. SPIRE Conf., Glasgow, UK pages 316--328. Google ScholarDigital Library
- Callan, J. (2000). Advances in information retrieval Chapter 5, Distributed information retrieval, pages 127--150. Kluwer.Google Scholar
- Callan, J. and Connell, M. (2001). Query-based sampling of text databases.ACM Transactions on Information Systems 19(2):97--130. Google ScholarDigital Library
- Callan, J., Lu, Z., and Croft, B. (1995). Searching distributed collections with inference networks. Proc. ACM SIGIR Conf., Seattle, WA pages 21--28. Google ScholarDigital Library
- Cho, J. and Garcia-Molina, H. (2003). Effective page refresh policies for web crawlers. ACM Transactions on Database Systems 28(4):390--426. Google ScholarDigital Library
- Craswell, N., Bailey, P., and Hawking, D. (2000). Server selection on the World Wide Web. Proc. ACM Conf. on Digital Libraries, San Antonio, TX pages 37--46. Google ScholarDigital Library
- Craswell, N., Crimmins, F., Hawking, D., and Moffat, A. (2004). Performance and cost tradeoffs in web search. In Proc. Australasian Database Conf., Darlinghurst, Australia pages 161--169, Australian Computer Society, Inc. Google ScholarDigital Library
- Gravano, L., Chang, C., Garcia-Molina, H., and Paepcke, A. (1997). Starts:Stanford proposal for internet meta-searching. In Proc. ACM SIGMOD Conf., Tucson, AZ pages 207--218. Google ScholarDigital Library
- Gravano, L., García-Molina, H., and Tomasic, A. (1999).GlOSS: text-source discovery over the Internet. ACM Transactions on Database Systems 24(2):229--264. Google ScholarDigital Library
- Gravano, L., Ipeirotis, P., and Sahami, M. (2003). Qprober: A system for automatic classification of hidden-web databases. ACM Transactions on Information Systems 21(1):1--41. Google ScholarDigital Library
- Hawking, D. and Thomas, P. (2005). Server selection methods in hybrid portal search. In Proc. ACM SIGIR Conf., Salvador, Brazil pages 75--82. Google ScholarDigital Library
- Ipeirotis, P., Ntoulas, A., Cho,J., and Gravano, L. (2005). Modeling and managing content changes in text databases. In Proc. ICDE Conf., Tokyo, Japan pages 606--617. Google ScholarDigital Library
- Kleinberg, J. (2006). Temporal dynamics of on-line information systems. Data Stream Management: Processing High-Speed Data Streams.Google Scholar
- S. Kullback. Information theoery and statistics. Wiley, New York, NY 1959.Google Scholar
- Ntoulas, A., Zerfos, P., and Cho, J. (2005). Downloading textual hidden web content through keyword queries. In Proc. ACM/IEEE-CS Joint Conf. on Digital libraries, Denver, CO pages 100--109. Google ScholarDigital Library
- Paepcke, A., Brandriff, R., Janee, G., Larson, R.,Ludaescher, B., Melnik, S., and Raghavan, S. (2000). Search middleware and the simple digital library interoperability protocol. D-Lib Magazine 6(3).Google Scholar
- Price, G. and Sherman, C. (2001). The Invisible Web: Uncovering Information Sources Search Engines Can't See CyberAge Books. Google ScholarDigital Library
- Robertson, S., Walker, S., Hancock-Beaulieu, M., Gull ,A., and Lau, M. (1992). Okapi at TREC. In Proceedings of TREC-1992, Gaithersburg, MA pages 21--30.Google Scholar
- Si, L. and Callan, J. (2003a). Relevant document distribution estimation method for resource selection. In Proc. ACM SIGIR Conf., Toronto, Canada pages 298--305. Google ScholarDigital Library
- Si, L. and Callan, J. (2003b). A semisupervised learning method to merge search engine results. ACM Transactions on Infor-mation Systems 21(4):457--491. Google ScholarDigital Library
- Si, L. and Callan, J. (2004). Unified utility maximization framework for resource selection. In Proc. ACM CIKM Conf., Washington, DC pages 32--41. Google ScholarDigital Library
- Si, L., Jin, R., Callan, J., and Ogilvie, P. (2002). A language modeling framework for resource selection and results merging. In Proc. ACM CIKM Conf., McLean, VA pages 391--397. Google ScholarDigital Library
- Shokouhi, M. (2007). Central-Rank-Based Collection Selection in uncooperative distributed information retrieval. Proc. ECIR Conf., Rome, Italy pages 160--172. Google ScholarDigital Library
- Shokouhi, M., Zobel, J., Tahaghoghi, S., and Scholer, F. (2007). Using query logs to establish vocabularies in distributed information retrieval. Journal of Information Processing and Management 43(1). Google ScholarDigital Library
- Shokouhi, M., Zobel, J., Scholer, F., and Tahaghoghi, S. (2006). Capturing collection size for distributed non-cooperative retrieval. In Proc. ACM SIGIR Conf., Seattle, WA pages 316--323. Google ScholarDigital Library
- J. Xu and J. Callan (1998). Effective retrieval with distributed collections.In Proc. ACM SIGIR Conf., Melbourne, Australia pages 112--120. Google ScholarDigital Library
- Xu, J. and Croft, W.B. (1999). Cluster-based language models for distributed retrieval. In Proc. ACM SIGIR Conf., Berkeley, CA pages 254--261. Google ScholarDigital Library
Index Terms
- Updating collection representations for federated search
Recommendations
Federated search in the wild: the combined power of over a hundred search engines
CIKM '12: Proceedings of the 21st ACM international conference on Information and knowledge managementFederated search has the potential of improving web search: the user becomes less dependent on a single search provider and parts of the deep web become available through a unified interface, leading to a wider variety in the retrieved search results. ...
A multi-collection latent topic model for federated search
AbstractCollection selection is a crucial function, central to the effectiveness and efficiency of a federated information retrieval system. A variety of solutions have been proposed for collection selection adapting proven techniques used in centralised ...
A Methodology for Collection Selection in Heterogeneous Contexts
ITCC '02: Proceedings of the International Conference on Information Technology: Coding and ComputingIn this paper we demonstrate that in an ideal Distributed Information Retrieval environment, taking the ability of each collection server to return relevant documents into account when selecting collections can be effective. Based on this assumption, we ...
Comments