Data fusion with estimated weight

S. Wu; F. Crestani

Data fusion with estimated weight

S. Wu, F. Crestani

Computer And Information Sciences

Research output: Contribution to conference › Paper › peer-review

44 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 language	English
Pages	648-651
Number of pages	3
Publication status	Published - 5 Nov 2002
Event	Proceedings of the eleventh international Conference on Information and Knowledge Management 2002 - McLean, USA Duration: 4 Nov 2002 → 9 Nov 2002

Conference

Conference	Proceedings of the eleventh international Conference on Information and Knowledge Management 2002
City	McLean, USA
Period	4/11/02 → 9/11/02

Keywords

data fusion
distributed information retrieval
metasearch
results merging

Cite this

@conference{4af569b1954a42c1ae68927f94c0e61b,

title = "Data fusion with estimated weight",

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.",

keywords = "data fusion, distributed information retrieval, metasearch, results merging",

author = "S. Wu and F. Crestani",

year = "2002",

month = nov,

day = "5",

language = "English",

pages = "648--651",

note = "Proceedings of the eleventh international Conference on Information and Knowledge Management 2002 ; Conference date: 04-11-2002 Through 09-11-2002",

}

TY - CONF

T1 - Data fusion with estimated weight

AU - Wu, S.

AU - Crestani, F.

PY - 2002/11/5

Y1 - 2002/11/5

N2 - 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.

AB - 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.

KW - data fusion

KW - distributed information retrieval

KW - metasearch

KW - results merging

UR - http://dx.doi.org/10.1145/584792.584908

M3 - Paper

SP - 648

EP - 651

T2 - Proceedings of the eleventh international Conference on Information and Knowledge Management 2002

Y2 - 4 November 2002 through 9 November 2002

ER -

Data fusion with estimated weight

Abstract

Conference

Keywords

Other files and links

Cite this