A Formal Model for Data Fusion

In information retrieval, the data fusion problem is as follows: given two or more independent retrieved sets of ranked documents in response to the same query, how to merge the sets in order to present the user with the most effective ranking? We propose a formal model for data fusion that is based on the knowledge that can be derived from the retrieved documents. The modelis based on evidential reasoning, a theory that formally expresses knowledge and the combination of knowledge. Knowledge characterising a ranked list of retrieved documents is symbolised. The combination of knowledge associated to the several retrieval results yields the characterisation of the merged result.

[1]  Garrison W. Cottrell,et al.  Automatic combination of multiple ranked retrieval systems , 1994, SIGIR '94.

[2]  Theo Huibers,et al.  An axiomatic theory for information retrieval , 1996 .

[3]  Paul B. Kantor,et al.  Data Fusion of Machine-Learning Methods for the TREC5 Routing Task (and other work) , 1996, TREC.

[4]  Guijun Wang,et al.  Information fusion with ProFusion , 1996, WebNet.

[5]  Ronald R. Yager,et al.  On the fusion of documents from multiple collection information retrieval systems , 1998 .

[6]  Brian F. Chellas.  Modal Logic: Normal systems of modal logic , 1980 .

[7]  Adele E. Howe,et al.  Experiences with selecting search engines using metasearch , 1997, TOIS.

[8]  Oren Etzioni,et al.  The MetaCrawler architecture for resource aggregation on the Web , 1997 .

[9]  Mounia Lalmas,et al.  Merging techniques for performing data fusion on the web , 2001, CIKM '01.

[10]  Christoph Baumgarten,et al.  A probabilistic model for distributed information retrieval , 1997, Annual International ACM SIGIR Conference on Research and Development in Information Retrieval.

[11]  Guijun Wang,et al.  ProFusion*: Intelligent Fusion from Multiple, Distributed Search Engines , 1996, J. Univers. Comput. Sci..

[12]  Luis Gravano,et al.  STARTS: Stanford proposal for Internet meta-searching , 1997, SIGMOD '97.

[13]  Ellen M. Voorhees,et al.  Learning collection fusion strategies , 1995, SIGIR '95.

[14]  Alan F. Smeaton.  Independence of Contributing Retrieval Strategies in Data Fusion for Effective Information Retrieval , 1998, BCS-IRSG Annual Colloquium on IR Research.

[15]  Jacques Savoy,et al.  Report on the TREC-5 Experiment: Data Fusion and Collection Fusion , 1996, TREC.