Exploiting query logs for cross-lingual query suggestion

Wei Gao, Cheng Niu, Jian Yun Nie, Ming Zhou, Kam Fai Wong, Hsiao Wuen Hon

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

Query suggestion aims to suggest relevant queries for a given query, which helps users better specify their information needs. Previous work on query suggestion has been limited to the same language. In this article, we extend it to cross-lingual query suggestion (CLQS): for a query in one language, we suggest similar or relevant queries in other languages. This is very important to the scenarios of cross-language information retrieval (CLIR) and other related cross-lingual applications. Instead of relying on existing query translation technologies for CLQS, we present an effective meanstomap the input query of one language to queries of the other language inthe query log. Important monolingual and cross-lingual information such as word translation relations and word co-occurrence statistics, and so on, are used to estimate the cross-lingual query similarity with a discriminative model. Benchmarks show that the resulting CLQS system significantly outperforms a baseline system that uses dictionary-based query translation. Besides, we evaluate CLQS with French-English and Chinese-English CLIR tasks on TREC-6 and NTCIR-4 collections, respectively. The CLIR experiments using typical retrieval models demonstrate that the CLQS-based approach has significantly higher effectiveness than several traditional query translation methods. We find that when combined with pseudo-relevance feedback, the effectiveness of CLIR using CLQS is enhanced for different pairs of languages.

Original languageEnglish
Article number6
JournalACM Transactions on Information Systems
Volume28
Issue number2
DOIs
Publication statusPublished - 1 May 2010
Externally publishedYes

Fingerprint

Query languages
Glossaries
Query logs
Query
Statistics
Feedback
Experiments
Language

Keywords

  • Cross-language information retrieval
  • Que log
  • Query expansion
  • Query suggestion
  • Query translation

ASJC Scopus subject areas

  • Information Systems
  • Business, Management and Accounting(all)
  • Computer Science Applications

Cite this

Exploiting query logs for cross-lingual query suggestion. / Gao, Wei; Niu, Cheng; Nie, Jian Yun; Zhou, Ming; Wong, Kam Fai; Hon, Hsiao Wuen.

In: ACM Transactions on Information Systems, Vol. 28, No. 2, 6, 01.05.2010.

Research output: Contribution to journalArticle

Gao, Wei ; Niu, Cheng ; Nie, Jian Yun ; Zhou, Ming ; Wong, Kam Fai ; Hon, Hsiao Wuen. / Exploiting query logs for cross-lingual query suggestion. In: ACM Transactions on Information Systems. 2010 ; Vol. 28, No. 2.
@article{343623adc1394242a1c87bfaa1e7c706,
title = "Exploiting query logs for cross-lingual query suggestion",
abstract = "Query suggestion aims to suggest relevant queries for a given query, which helps users better specify their information needs. Previous work on query suggestion has been limited to the same language. In this article, we extend it to cross-lingual query suggestion (CLQS): for a query in one language, we suggest similar or relevant queries in other languages. This is very important to the scenarios of cross-language information retrieval (CLIR) and other related cross-lingual applications. Instead of relying on existing query translation technologies for CLQS, we present an effective meanstomap the input query of one language to queries of the other language inthe query log. Important monolingual and cross-lingual information such as word translation relations and word co-occurrence statistics, and so on, are used to estimate the cross-lingual query similarity with a discriminative model. Benchmarks show that the resulting CLQS system significantly outperforms a baseline system that uses dictionary-based query translation. Besides, we evaluate CLQS with French-English and Chinese-English CLIR tasks on TREC-6 and NTCIR-4 collections, respectively. The CLIR experiments using typical retrieval models demonstrate that the CLQS-based approach has significantly higher effectiveness than several traditional query translation methods. We find that when combined with pseudo-relevance feedback, the effectiveness of CLIR using CLQS is enhanced for different pairs of languages.",
keywords = "Cross-language information retrieval, Que log, Query expansion, Query suggestion, Query translation",
author = "Wei Gao and Cheng Niu and Nie, {Jian Yun} and Ming Zhou and Wong, {Kam Fai} and Hon, {Hsiao Wuen}",
year = "2010",
month = "5",
day = "1",
doi = "10.1145/1740592.1740594",
language = "English",
volume = "28",
journal = "ACM Transactions on Information Systems",
issn = "1046-8188",
publisher = "Association for Computing Machinery (ACM)",
number = "2",

}

TY - JOUR

T1 - Exploiting query logs for cross-lingual query suggestion

AU - Gao, Wei

AU - Niu, Cheng

AU - Nie, Jian Yun

AU - Zhou, Ming

AU - Wong, Kam Fai

AU - Hon, Hsiao Wuen

PY - 2010/5/1

Y1 - 2010/5/1

N2 - Query suggestion aims to suggest relevant queries for a given query, which helps users better specify their information needs. Previous work on query suggestion has been limited to the same language. In this article, we extend it to cross-lingual query suggestion (CLQS): for a query in one language, we suggest similar or relevant queries in other languages. This is very important to the scenarios of cross-language information retrieval (CLIR) and other related cross-lingual applications. Instead of relying on existing query translation technologies for CLQS, we present an effective meanstomap the input query of one language to queries of the other language inthe query log. Important monolingual and cross-lingual information such as word translation relations and word co-occurrence statistics, and so on, are used to estimate the cross-lingual query similarity with a discriminative model. Benchmarks show that the resulting CLQS system significantly outperforms a baseline system that uses dictionary-based query translation. Besides, we evaluate CLQS with French-English and Chinese-English CLIR tasks on TREC-6 and NTCIR-4 collections, respectively. The CLIR experiments using typical retrieval models demonstrate that the CLQS-based approach has significantly higher effectiveness than several traditional query translation methods. We find that when combined with pseudo-relevance feedback, the effectiveness of CLIR using CLQS is enhanced for different pairs of languages.

AB - Query suggestion aims to suggest relevant queries for a given query, which helps users better specify their information needs. Previous work on query suggestion has been limited to the same language. In this article, we extend it to cross-lingual query suggestion (CLQS): for a query in one language, we suggest similar or relevant queries in other languages. This is very important to the scenarios of cross-language information retrieval (CLIR) and other related cross-lingual applications. Instead of relying on existing query translation technologies for CLQS, we present an effective meanstomap the input query of one language to queries of the other language inthe query log. Important monolingual and cross-lingual information such as word translation relations and word co-occurrence statistics, and so on, are used to estimate the cross-lingual query similarity with a discriminative model. Benchmarks show that the resulting CLQS system significantly outperforms a baseline system that uses dictionary-based query translation. Besides, we evaluate CLQS with French-English and Chinese-English CLIR tasks on TREC-6 and NTCIR-4 collections, respectively. The CLIR experiments using typical retrieval models demonstrate that the CLQS-based approach has significantly higher effectiveness than several traditional query translation methods. We find that when combined with pseudo-relevance feedback, the effectiveness of CLIR using CLQS is enhanced for different pairs of languages.

KW - Cross-language information retrieval

KW - Que log

KW - Query expansion

KW - Query suggestion

KW - Query translation

UR - http://www.scopus.com/inward/record.url?scp=78651327029&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78651327029&partnerID=8YFLogxK

U2 - 10.1145/1740592.1740594

DO - 10.1145/1740592.1740594

M3 - Article

VL - 28

JO - ACM Transactions on Information Systems

JF - ACM Transactions on Information Systems

SN - 1046-8188

IS - 2

M1 - 6

ER -