Applying statistical principles to data fusion in information retrieval

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Data fusion in information retrieval has been investigated by many researchers and quite a few data fusion methods have been proposed. However, their impact on effectiveness has not been well understood. In this paper, we apply statistical principles to data fusion and present a statistical data fusion model, which specifies the algorithm for fusion and conditions to be satisfied. The statistical model can be used as a guideline for data fusion methods. Based on this analysis, we compare CombSum and CombMNZ, which are the two best-known data fusion methods. We explain why sometimes CombMNZ does outperform Comb- Sum and what can be done to make CombSum more effective. Experimental results with TREC data are reported to support the conclusion that our enhancements to the algorithm improve effectiveness.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages313-319
Number of pages7
DOIs
Publication statusPublished - 2007
EventIEEE International Conference on Systems, Man and Cybernetics, 2007 - Montreal, Canada
Duration: 1 Jan 2007 → …

Conference

ConferenceIEEE International Conference on Systems, Man and Cybernetics, 2007
Period1/01/07 → …

Fingerprint

Data fusion
Information retrieval

Cite this

@inproceedings{9d2747ede6e54a9cbc0c8a3f710b288e,
title = "Applying statistical principles to data fusion in information retrieval",
abstract = "Data fusion in information retrieval has been investigated by many researchers and quite a few data fusion methods have been proposed. However, their impact on effectiveness has not been well understood. In this paper, we apply statistical principles to data fusion and present a statistical data fusion model, which specifies the algorithm for fusion and conditions to be satisfied. The statistical model can be used as a guideline for data fusion methods. Based on this analysis, we compare CombSum and CombMNZ, which are the two best-known data fusion methods. We explain why sometimes CombMNZ does outperform Comb- Sum and what can be done to make CombSum more effective. Experimental results with TREC data are reported to support the conclusion that our enhancements to the algorithm improve effectiveness.",
author = "Shengli Wu and Yaxin Bi and Sally McClean",
year = "2007",
doi = "10.1109/ICSMC.2007.4413590",
language = "English",
isbn = "978-1-4244-0991-4",
pages = "313--319",
booktitle = "Unknown Host Publication",

}

Wu, S, Bi, Y & McClean, S 2007, Applying statistical principles to data fusion in information retrieval. in Unknown Host Publication. pp. 313-319, IEEE International Conference on Systems, Man and Cybernetics, 2007, 1/01/07. https://doi.org/10.1109/ICSMC.2007.4413590

Applying statistical principles to data fusion in information retrieval. / Wu, Shengli; Bi, Yaxin; McClean, Sally.

Unknown Host Publication. 2007. p. 313-319.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Applying statistical principles to data fusion in information retrieval

AU - Wu, Shengli

AU - Bi, Yaxin

AU - McClean, Sally

PY - 2007

Y1 - 2007

N2 - Data fusion in information retrieval has been investigated by many researchers and quite a few data fusion methods have been proposed. However, their impact on effectiveness has not been well understood. In this paper, we apply statistical principles to data fusion and present a statistical data fusion model, which specifies the algorithm for fusion and conditions to be satisfied. The statistical model can be used as a guideline for data fusion methods. Based on this analysis, we compare CombSum and CombMNZ, which are the two best-known data fusion methods. We explain why sometimes CombMNZ does outperform Comb- Sum and what can be done to make CombSum more effective. Experimental results with TREC data are reported to support the conclusion that our enhancements to the algorithm improve effectiveness.

AB - Data fusion in information retrieval has been investigated by many researchers and quite a few data fusion methods have been proposed. However, their impact on effectiveness has not been well understood. In this paper, we apply statistical principles to data fusion and present a statistical data fusion model, which specifies the algorithm for fusion and conditions to be satisfied. The statistical model can be used as a guideline for data fusion methods. Based on this analysis, we compare CombSum and CombMNZ, which are the two best-known data fusion methods. We explain why sometimes CombMNZ does outperform Comb- Sum and what can be done to make CombSum more effective. Experimental results with TREC data are reported to support the conclusion that our enhancements to the algorithm improve effectiveness.

U2 - 10.1109/ICSMC.2007.4413590

DO - 10.1109/ICSMC.2007.4413590

M3 - Conference contribution

SN - 978-1-4244-0991-4

SP - 313

EP - 319

BT - Unknown Host Publication

ER -