Information retrieval using word senses: Root sense tagging approach

Sang Bum Kim, Hee Cheol Seo, Hae-Chang Rim

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

69 Citations (Scopus)

Abstract

Information retrieval using word senses is emerging as a good research challenge on semantic information retrieval. In this paper, we propose a new method using word senses in information retrieval: root sense tagging method. This method assigns coarse-grained word senses defined in WordNet to query terms and document terms by unsupervised way using co-occurrence information constructed automatically. Our sense tagger is crude, but performs consistent disambiguation by considering only the single most informative word as evidence to disambiguate the target word. We also allow multiple-sense assignment to alleviate the problem caused by incorrect disambiguation. Experimental results on a large-scale TREC collection show that our approach to improve retrieval effectiveness is successful, while most of the previous work failed to improve performances even on small text collection. Our method also shows promising results when is combined with pseudo relevance feedback and state-of-the-art retrieval function such as BM25.

Original languageEnglish
Title of host publicationProceedings of Sheffield SIGIR - Twenty-Seventh Annual International ACM SIGIR Conference on Research and Development in Information Retrieval
EditorsK. Jarvelin, J. Allen, P. Bruza, M. Sanderson
Pages258-265
Number of pages8
Publication statusPublished - 2004 Nov 25
EventProceedings of Sheffield SIGIR - Twenty-Seventh Annual International ACM SIGIR Conference on Research and Development in Information Retrieval - Sheffield, United Kingdom
Duration: 2004 Jul 252004 Jul 29

Other

OtherProceedings of Sheffield SIGIR - Twenty-Seventh Annual International ACM SIGIR Conference on Research and Development in Information Retrieval
CountryUnited Kingdom
CitySheffield
Period04/7/2504/7/29

Fingerprint

Information retrieval
Semantics
Feedback

Keywords

  • Information retrieval
  • Performance evaluation
  • Word sense disambiguation
  • WordNet

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Kim, S. B., Seo, H. C., & Rim, H-C. (2004). Information retrieval using word senses: Root sense tagging approach. In K. Jarvelin, J. Allen, P. Bruza, & M. Sanderson (Eds.), Proceedings of Sheffield SIGIR - Twenty-Seventh Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 258-265)

Information retrieval using word senses : Root sense tagging approach. / Kim, Sang Bum; Seo, Hee Cheol; Rim, Hae-Chang.

Proceedings of Sheffield SIGIR - Twenty-Seventh Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. ed. / K. Jarvelin; J. Allen; P. Bruza; M. Sanderson. 2004. p. 258-265.

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

Kim, SB, Seo, HC & Rim, H-C 2004, Information retrieval using word senses: Root sense tagging approach. in K Jarvelin, J Allen, P Bruza & M Sanderson (eds), Proceedings of Sheffield SIGIR - Twenty-Seventh Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 258-265, Proceedings of Sheffield SIGIR - Twenty-Seventh Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Sheffield, United Kingdom, 04/7/25.
Kim SB, Seo HC, Rim H-C. Information retrieval using word senses: Root sense tagging approach. In Jarvelin K, Allen J, Bruza P, Sanderson M, editors, Proceedings of Sheffield SIGIR - Twenty-Seventh Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. 2004. p. 258-265
Kim, Sang Bum ; Seo, Hee Cheol ; Rim, Hae-Chang. / Information retrieval using word senses : Root sense tagging approach. Proceedings of Sheffield SIGIR - Twenty-Seventh Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. editor / K. Jarvelin ; J. Allen ; P. Bruza ; M. Sanderson. 2004. pp. 258-265
@inproceedings{13648f4357d44b7ba15c3e1308bc3a6d,
title = "Information retrieval using word senses: Root sense tagging approach",
abstract = "Information retrieval using word senses is emerging as a good research challenge on semantic information retrieval. In this paper, we propose a new method using word senses in information retrieval: root sense tagging method. This method assigns coarse-grained word senses defined in WordNet to query terms and document terms by unsupervised way using co-occurrence information constructed automatically. Our sense tagger is crude, but performs consistent disambiguation by considering only the single most informative word as evidence to disambiguate the target word. We also allow multiple-sense assignment to alleviate the problem caused by incorrect disambiguation. Experimental results on a large-scale TREC collection show that our approach to improve retrieval effectiveness is successful, while most of the previous work failed to improve performances even on small text collection. Our method also shows promising results when is combined with pseudo relevance feedback and state-of-the-art retrieval function such as BM25.",
keywords = "Information retrieval, Performance evaluation, Word sense disambiguation, WordNet",
author = "Kim, {Sang Bum} and Seo, {Hee Cheol} and Hae-Chang Rim",
year = "2004",
month = "11",
day = "25",
language = "English",
isbn = "1581138814",
pages = "258--265",
editor = "K. Jarvelin and J. Allen and P. Bruza and M. Sanderson",
booktitle = "Proceedings of Sheffield SIGIR - Twenty-Seventh Annual International ACM SIGIR Conference on Research and Development in Information Retrieval",

}

TY - GEN

T1 - Information retrieval using word senses

T2 - Root sense tagging approach

AU - Kim, Sang Bum

AU - Seo, Hee Cheol

AU - Rim, Hae-Chang

PY - 2004/11/25

Y1 - 2004/11/25

N2 - Information retrieval using word senses is emerging as a good research challenge on semantic information retrieval. In this paper, we propose a new method using word senses in information retrieval: root sense tagging method. This method assigns coarse-grained word senses defined in WordNet to query terms and document terms by unsupervised way using co-occurrence information constructed automatically. Our sense tagger is crude, but performs consistent disambiguation by considering only the single most informative word as evidence to disambiguate the target word. We also allow multiple-sense assignment to alleviate the problem caused by incorrect disambiguation. Experimental results on a large-scale TREC collection show that our approach to improve retrieval effectiveness is successful, while most of the previous work failed to improve performances even on small text collection. Our method also shows promising results when is combined with pseudo relevance feedback and state-of-the-art retrieval function such as BM25.

AB - Information retrieval using word senses is emerging as a good research challenge on semantic information retrieval. In this paper, we propose a new method using word senses in information retrieval: root sense tagging method. This method assigns coarse-grained word senses defined in WordNet to query terms and document terms by unsupervised way using co-occurrence information constructed automatically. Our sense tagger is crude, but performs consistent disambiguation by considering only the single most informative word as evidence to disambiguate the target word. We also allow multiple-sense assignment to alleviate the problem caused by incorrect disambiguation. Experimental results on a large-scale TREC collection show that our approach to improve retrieval effectiveness is successful, while most of the previous work failed to improve performances even on small text collection. Our method also shows promising results when is combined with pseudo relevance feedback and state-of-the-art retrieval function such as BM25.

KW - Information retrieval

KW - Performance evaluation

KW - Word sense disambiguation

KW - WordNet

UR - http://www.scopus.com/inward/record.url?scp=8644292630&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=8644292630&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:8644292630

SN - 1581138814

SP - 258

EP - 265

BT - Proceedings of Sheffield SIGIR - Twenty-Seventh Annual International ACM SIGIR Conference on Research and Development in Information Retrieval

A2 - Jarvelin, K.

A2 - Allen, J.

A2 - Bruza, P.

A2 - Sanderson, M.

ER -