The weighted Condorcet fusion in information retrieval

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

The Condorcet fusion is a distinctive fusion method and was found usefulin information retrieval. Two basic requirements for the Condorcet fusion to improveretrieval effectiveness are: 1. all component systems involved should be more or less equally effective; 2. each information retrieval system should be developedindependently and thus each component result is more or less equally differentfrom the others. These two requirements may not be satisfied in many cases, thenweighted Condorcet becomes a good option. However, how to assign weights for the weighted Condorcet has not been investigated. In this paper, we present a linear discriminant analysis (LDA) based approachto training weights. Some properties of Condorcet fusionand weighted Condorcet fusion are discussed. Experiments are conductedwith three groups of runs submitted to TREC to evaluate the performance of a group of data fusion methods. The empirical investigation finds that Condorcet fusion is a good ranking-based method in good conditions, while weighted Condorcet fusion can make significant improvement over Condorcet fusion when the conditions are not favourable for Condorcet fusion. The experiments alsoshow that the proposed LDA weighting schema is effective and Condorcet fusion with LDA based weighting schema is more effective than all other data fusion methods involved.
LanguageEnglish
Pages108-122
JournalInformation Processing & Management
Volume49
Issue number1
DOIs
Publication statusPublished - 1 Jan 2013

Fingerprint

Discriminant analysis
Information retrieval
Data fusion
Information retrieval systems
Experiments

Keywords

  • Data fusion
  • Information retrieval
  • Condorcet
  • Weighted Condorcet
  • Weight assignment
  • Linear discriminant analysis

Cite this

@article{e7e0c0a842c54937b2a0225450606dbb,
title = "The weighted Condorcet fusion in information retrieval",
abstract = "The Condorcet fusion is a distinctive fusion method and was found usefulin information retrieval. Two basic requirements for the Condorcet fusion to improveretrieval effectiveness are: 1. all component systems involved should be more or less equally effective; 2. each information retrieval system should be developedindependently and thus each component result is more or less equally differentfrom the others. These two requirements may not be satisfied in many cases, thenweighted Condorcet becomes a good option. However, how to assign weights for the weighted Condorcet has not been investigated. In this paper, we present a linear discriminant analysis (LDA) based approachto training weights. Some properties of Condorcet fusionand weighted Condorcet fusion are discussed. Experiments are conductedwith three groups of runs submitted to TREC to evaluate the performance of a group of data fusion methods. The empirical investigation finds that Condorcet fusion is a good ranking-based method in good conditions, while weighted Condorcet fusion can make significant improvement over Condorcet fusion when the conditions are not favourable for Condorcet fusion. The experiments alsoshow that the proposed LDA weighting schema is effective and Condorcet fusion with LDA based weighting schema is more effective than all other data fusion methods involved.",
keywords = "Data fusion, Information retrieval, Condorcet, Weighted Condorcet, Weight assignment, Linear discriminant analysis",
author = "Shengli Wu",
year = "2013",
month = "1",
day = "1",
doi = "10.1016/j.ipm.2012.02.007",
language = "English",
volume = "49",
pages = "108--122",
number = "1",

}

The weighted Condorcet fusion in information retrieval. / Wu, Shengli.

Vol. 49, No. 1, 01.01.2013, p. 108-122.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The weighted Condorcet fusion in information retrieval

AU - Wu, Shengli

PY - 2013/1/1

Y1 - 2013/1/1

N2 - The Condorcet fusion is a distinctive fusion method and was found usefulin information retrieval. Two basic requirements for the Condorcet fusion to improveretrieval effectiveness are: 1. all component systems involved should be more or less equally effective; 2. each information retrieval system should be developedindependently and thus each component result is more or less equally differentfrom the others. These two requirements may not be satisfied in many cases, thenweighted Condorcet becomes a good option. However, how to assign weights for the weighted Condorcet has not been investigated. In this paper, we present a linear discriminant analysis (LDA) based approachto training weights. Some properties of Condorcet fusionand weighted Condorcet fusion are discussed. Experiments are conductedwith three groups of runs submitted to TREC to evaluate the performance of a group of data fusion methods. The empirical investigation finds that Condorcet fusion is a good ranking-based method in good conditions, while weighted Condorcet fusion can make significant improvement over Condorcet fusion when the conditions are not favourable for Condorcet fusion. The experiments alsoshow that the proposed LDA weighting schema is effective and Condorcet fusion with LDA based weighting schema is more effective than all other data fusion methods involved.

AB - The Condorcet fusion is a distinctive fusion method and was found usefulin information retrieval. Two basic requirements for the Condorcet fusion to improveretrieval effectiveness are: 1. all component systems involved should be more or less equally effective; 2. each information retrieval system should be developedindependently and thus each component result is more or less equally differentfrom the others. These two requirements may not be satisfied in many cases, thenweighted Condorcet becomes a good option. However, how to assign weights for the weighted Condorcet has not been investigated. In this paper, we present a linear discriminant analysis (LDA) based approachto training weights. Some properties of Condorcet fusionand weighted Condorcet fusion are discussed. Experiments are conductedwith three groups of runs submitted to TREC to evaluate the performance of a group of data fusion methods. The empirical investigation finds that Condorcet fusion is a good ranking-based method in good conditions, while weighted Condorcet fusion can make significant improvement over Condorcet fusion when the conditions are not favourable for Condorcet fusion. The experiments alsoshow that the proposed LDA weighting schema is effective and Condorcet fusion with LDA based weighting schema is more effective than all other data fusion methods involved.

KW - Data fusion

KW - Information retrieval

KW - Condorcet

KW - Weighted Condorcet

KW - Weight assignment

KW - Linear discriminant analysis

U2 - 10.1016/j.ipm.2012.02.007

DO - 10.1016/j.ipm.2012.02.007

M3 - Article

VL - 49

SP - 108

EP - 122

IS - 1

ER -