MT-based Japanese-English cross-language IR experiments using the TREC test collections

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

7 Citations (Scopus)

Abstract

This paper evaluates the effectiveness of MT-based Japanese-English CLIR using a subcollection of the TREC test collections and two bilingual researchers to separately translate the TREC requests into Japanese. Our main findings are as follows: (1)With the aid of pseudo-relevance feedback, MT-based J-E CLIR can be as effective as "best-case" monolingual IR. In particular, although poor MT quality often leads to poor initial CLIR performance, pseudo-relevance feedback is useful for alleviating the harm; (2)The manual request translation process that is inherent in conventional CLIR performance evaluation can be a more dominant factor than query length and overall MT quality.

Original languageEnglish
Title of host publicationProceedings of the 5th international Workshop on Information Retrieval with Asian Languages, IRAL 2000
PublisherAssociation for Computing Machinery, Inc
Pages181-188
Number of pages8
ISBN (Electronic)1581133006, 9781581133004
DOIs
Publication statusPublished - 2000 Nov 1
Externally publishedYes
Event5th International Workshop on Information Retrieval with Asian Languages, IRAL 2000 - Hong Kong, China
Duration: 2000 Sep 302000 Oct 1

Other

Other5th International Workshop on Information Retrieval with Asian Languages, IRAL 2000
CountryChina
CityHong Kong
Period00/9/3000/10/1

Fingerprint

Feedback
Experiments

Keywords

  • Cross-language information retrieval
  • Machine translation

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems

Cite this

Sakai, T. (2000). MT-based Japanese-English cross-language IR experiments using the TREC test collections. In Proceedings of the 5th international Workshop on Information Retrieval with Asian Languages, IRAL 2000 (pp. 181-188). Association for Computing Machinery, Inc. https://doi.org/10.1145/355214.355240

MT-based Japanese-English cross-language IR experiments using the TREC test collections. / Sakai, Tetsuya.

Proceedings of the 5th international Workshop on Information Retrieval with Asian Languages, IRAL 2000. Association for Computing Machinery, Inc, 2000. p. 181-188.

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

Sakai, T 2000, MT-based Japanese-English cross-language IR experiments using the TREC test collections. in Proceedings of the 5th international Workshop on Information Retrieval with Asian Languages, IRAL 2000. Association for Computing Machinery, Inc, pp. 181-188, 5th International Workshop on Information Retrieval with Asian Languages, IRAL 2000, Hong Kong, China, 00/9/30. https://doi.org/10.1145/355214.355240
Sakai T. MT-based Japanese-English cross-language IR experiments using the TREC test collections. In Proceedings of the 5th international Workshop on Information Retrieval with Asian Languages, IRAL 2000. Association for Computing Machinery, Inc. 2000. p. 181-188 https://doi.org/10.1145/355214.355240
Sakai, Tetsuya. / MT-based Japanese-English cross-language IR experiments using the TREC test collections. Proceedings of the 5th international Workshop on Information Retrieval with Asian Languages, IRAL 2000. Association for Computing Machinery, Inc, 2000. pp. 181-188
@inproceedings{747ef69517e64c96b673deb314e38b95,
title = "MT-based Japanese-English cross-language IR experiments using the TREC test collections",
abstract = "This paper evaluates the effectiveness of MT-based Japanese-English CLIR using a subcollection of the TREC test collections and two bilingual researchers to separately translate the TREC requests into Japanese. Our main findings are as follows: (1)With the aid of pseudo-relevance feedback, MT-based J-E CLIR can be as effective as {"}best-case{"} monolingual IR. In particular, although poor MT quality often leads to poor initial CLIR performance, pseudo-relevance feedback is useful for alleviating the harm; (2)The manual request translation process that is inherent in conventional CLIR performance evaluation can be a more dominant factor than query length and overall MT quality.",
keywords = "Cross-language information retrieval, Machine translation",
author = "Tetsuya Sakai",
year = "2000",
month = "11",
day = "1",
doi = "10.1145/355214.355240",
language = "English",
pages = "181--188",
booktitle = "Proceedings of the 5th international Workshop on Information Retrieval with Asian Languages, IRAL 2000",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - MT-based Japanese-English cross-language IR experiments using the TREC test collections

AU - Sakai, Tetsuya

PY - 2000/11/1

Y1 - 2000/11/1

N2 - This paper evaluates the effectiveness of MT-based Japanese-English CLIR using a subcollection of the TREC test collections and two bilingual researchers to separately translate the TREC requests into Japanese. Our main findings are as follows: (1)With the aid of pseudo-relevance feedback, MT-based J-E CLIR can be as effective as "best-case" monolingual IR. In particular, although poor MT quality often leads to poor initial CLIR performance, pseudo-relevance feedback is useful for alleviating the harm; (2)The manual request translation process that is inherent in conventional CLIR performance evaluation can be a more dominant factor than query length and overall MT quality.

AB - This paper evaluates the effectiveness of MT-based Japanese-English CLIR using a subcollection of the TREC test collections and two bilingual researchers to separately translate the TREC requests into Japanese. Our main findings are as follows: (1)With the aid of pseudo-relevance feedback, MT-based J-E CLIR can be as effective as "best-case" monolingual IR. In particular, although poor MT quality often leads to poor initial CLIR performance, pseudo-relevance feedback is useful for alleviating the harm; (2)The manual request translation process that is inherent in conventional CLIR performance evaluation can be a more dominant factor than query length and overall MT quality.

KW - Cross-language information retrieval

KW - Machine translation

UR - http://www.scopus.com/inward/record.url?scp=62849112866&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=62849112866&partnerID=8YFLogxK

U2 - 10.1145/355214.355240

DO - 10.1145/355214.355240

M3 - Conference contribution

AN - SCOPUS:62849112866

SP - 181

EP - 188

BT - Proceedings of the 5th international Workshop on Information Retrieval with Asian Languages, IRAL 2000

PB - Association for Computing Machinery, Inc

ER -