Data fusion with estimated weight

S. Wu, F. Crestani

Research output: Contribution to conferencePaper

42 Citations (Scopus)

Abstract

This paper proposes an adptive approach for data fusion of information retrieval systems, which exploits estimated performances of all component input systems without relevance judgement or training. The estimation is conducted prior to the fusion but uses the same data as fusion applies. The experiment shows that our algorithms are competitive with, and often outperform CombMNZ, one of the most effective algorithms in use.
Original languageEnglish
Pages648-651
Number of pages3
Publication statusPublished - 5 Nov 2002
EventProceedings of the eleventh international Conference on Information and Knowledge Management 2002 - McLean, USA
Duration: 4 Nov 20029 Nov 2002

Conference

ConferenceProceedings of the eleventh international Conference on Information and Knowledge Management 2002
CityMcLean, USA
Period4/11/029/11/02

Keywords

  • data fusion
  • distributed information retrieval
  • metasearch
  • results merging

Fingerprint Dive into the research topics of 'Data fusion with estimated weight'. Together they form a unique fingerprint.

  • Cite this

    Wu, S., & Crestani, F. (2002). Data fusion with estimated weight. 648-651. Paper presented at Proceedings of the eleventh international Conference on Information and Knowledge Management 2002, McLean, USA, .