Adaptive data fusion methods in information retrieval

S Wu, J Li, X Zeng, Y Bi

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Data fusion is currently used extensively in information retrievalfor various tasks. It has proved to be a useful technology because it is able to improve retrieval performance frequently. However, in almost all prior research in data fusion, static search environments have been used, and dynamic search environments have generally not been considered.In this paper, we investigate adaptive data fusion methods that can changetheir behavior when the search environment changes.Three adaptive data fusion methods are proposed and investigated.In order to test these proposed methods properly, we generate a benchmark from ahistorical TREC data set. Experiments with the benchmark show that two of theproposed methods are good and may potentially be used in practice.
LanguageEnglish
Pages2048-2061
JournalJournal of the Association for Information Science and Technology
Volume65
Issue number10
DOIs
Publication statusPublished - 1 Oct 2014

Fingerprint

Data fusion
Information retrieval
Experiments

Cite this

Wu, S ; Li, J ; Zeng, X ; Bi, Y. / Adaptive data fusion methods in information retrieval. 2014 ; Vol. 65, No. 10. pp. 2048-2061.
@article{5bddfb33e3084f3f806845dedcf7d7c0,
title = "Adaptive data fusion methods in information retrieval",
abstract = "Data fusion is currently used extensively in information retrievalfor various tasks. It has proved to be a useful technology because it is able to improve retrieval performance frequently. However, in almost all prior research in data fusion, static search environments have been used, and dynamic search environments have generally not been considered.In this paper, we investigate adaptive data fusion methods that can changetheir behavior when the search environment changes.Three adaptive data fusion methods are proposed and investigated.In order to test these proposed methods properly, we generate a benchmark from ahistorical TREC data set. Experiments with the benchmark show that two of theproposed methods are good and may potentially be used in practice.",
author = "S Wu and J Li and X Zeng and Y Bi",
year = "2014",
month = "10",
day = "1",
doi = "10.1002/asi.23140",
language = "English",
volume = "65",
pages = "2048--2061",
number = "10",

}

Adaptive data fusion methods in information retrieval. / Wu, S; Li, J; Zeng, X; Bi, Y.

Vol. 65, No. 10, 01.10.2014, p. 2048-2061.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Adaptive data fusion methods in information retrieval

AU - Wu, S

AU - Li, J

AU - Zeng, X

AU - Bi, Y

PY - 2014/10/1

Y1 - 2014/10/1

N2 - Data fusion is currently used extensively in information retrievalfor various tasks. It has proved to be a useful technology because it is able to improve retrieval performance frequently. However, in almost all prior research in data fusion, static search environments have been used, and dynamic search environments have generally not been considered.In this paper, we investigate adaptive data fusion methods that can changetheir behavior when the search environment changes.Three adaptive data fusion methods are proposed and investigated.In order to test these proposed methods properly, we generate a benchmark from ahistorical TREC data set. Experiments with the benchmark show that two of theproposed methods are good and may potentially be used in practice.

AB - Data fusion is currently used extensively in information retrievalfor various tasks. It has proved to be a useful technology because it is able to improve retrieval performance frequently. However, in almost all prior research in data fusion, static search environments have been used, and dynamic search environments have generally not been considered.In this paper, we investigate adaptive data fusion methods that can changetheir behavior when the search environment changes.Three adaptive data fusion methods are proposed and investigated.In order to test these proposed methods properly, we generate a benchmark from ahistorical TREC data set. Experiments with the benchmark show that two of theproposed methods are good and may potentially be used in practice.

U2 - 10.1002/asi.23140

DO - 10.1002/asi.23140

M3 - Article

VL - 65

SP - 2048

EP - 2061

IS - 10

ER -