Hybrid approach of query and document translation with pivot language for cross-language information retrieval

Kazuaki Kishida, Noriko Kando

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

Abstract

This paper reports experimental results of cross-language information retrieval (CLIR) from German to French, in which a hybrid approach of query and document translation was attempted, i.e, combining results of query translation (German to French) and of document translation (French to German). In order to avoid too high complexity of computation for translating a large amount of texts in documents, we executed pseudo-translation, i.e., a simple replacement of terms by a bilingual dictionary (for query translation, a machine translation system was used). In particular, since English was used as an intermediary language for both translation directions of German and French, English translations at the middle stage were employed as document representations in order to reduce the number of translation steps. By omitting a translation step (English to German), the performance was improved. Unfortunately, our hybrid approach could not show better performance than a simple query translation. This may be due to the low performance of document translation, which was carried out by a simple replacement of terms using a bilingual dictionary with no term disambiguation.

Original languageEnglish
Title of host publicationCEUR Workshop Proceedings
PublisherCEUR-WS
Volume1171
Publication statusPublished - 2005
Externally publishedYes
Event2005 Cross Language Evaluation Forum Workshop, CLEF 2005, co-located with the 9th European Conference on Digital Libraries, ECDL 2005 - Wien, Austria
Duration: 2005 Sep 212005 Sep 22

Other

Other2005 Cross Language Evaluation Forum Workshop, CLEF 2005, co-located with the 9th European Conference on Digital Libraries, ECDL 2005
CountryAustria
CityWien
Period05/9/2105/9/22

Fingerprint

Query languages
Glossaries

Keywords

  • Cross-language information retrieval
  • Document translation
  • Hybrid approach
  • Query translation

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Hybrid approach of query and document translation with pivot language for cross-language information retrieval. / Kishida, Kazuaki; Kando, Noriko.

CEUR Workshop Proceedings. Vol. 1171 CEUR-WS, 2005.

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

Kishida, K & Kando, N 2005, Hybrid approach of query and document translation with pivot language for cross-language information retrieval. in CEUR Workshop Proceedings. vol. 1171, CEUR-WS, 2005 Cross Language Evaluation Forum Workshop, CLEF 2005, co-located with the 9th European Conference on Digital Libraries, ECDL 2005, Wien, Austria, 05/9/21.
@inproceedings{1c5721ec8f1b40bd83cf195957a819b3,
title = "Hybrid approach of query and document translation with pivot language for cross-language information retrieval",
abstract = "This paper reports experimental results of cross-language information retrieval (CLIR) from German to French, in which a hybrid approach of query and document translation was attempted, i.e, combining results of query translation (German to French) and of document translation (French to German). In order to avoid too high complexity of computation for translating a large amount of texts in documents, we executed pseudo-translation, i.e., a simple replacement of terms by a bilingual dictionary (for query translation, a machine translation system was used). In particular, since English was used as an intermediary language for both translation directions of German and French, English translations at the middle stage were employed as document representations in order to reduce the number of translation steps. By omitting a translation step (English to German), the performance was improved. Unfortunately, our hybrid approach could not show better performance than a simple query translation. This may be due to the low performance of document translation, which was carried out by a simple replacement of terms using a bilingual dictionary with no term disambiguation.",
keywords = "Cross-language information retrieval, Document translation, Hybrid approach, Query translation",
author = "Kazuaki Kishida and Noriko Kando",
year = "2005",
language = "English",
volume = "1171",
booktitle = "CEUR Workshop Proceedings",
publisher = "CEUR-WS",

}

TY - GEN

T1 - Hybrid approach of query and document translation with pivot language for cross-language information retrieval

AU - Kishida, Kazuaki

AU - Kando, Noriko

PY - 2005

Y1 - 2005

N2 - This paper reports experimental results of cross-language information retrieval (CLIR) from German to French, in which a hybrid approach of query and document translation was attempted, i.e, combining results of query translation (German to French) and of document translation (French to German). In order to avoid too high complexity of computation for translating a large amount of texts in documents, we executed pseudo-translation, i.e., a simple replacement of terms by a bilingual dictionary (for query translation, a machine translation system was used). In particular, since English was used as an intermediary language for both translation directions of German and French, English translations at the middle stage were employed as document representations in order to reduce the number of translation steps. By omitting a translation step (English to German), the performance was improved. Unfortunately, our hybrid approach could not show better performance than a simple query translation. This may be due to the low performance of document translation, which was carried out by a simple replacement of terms using a bilingual dictionary with no term disambiguation.

AB - This paper reports experimental results of cross-language information retrieval (CLIR) from German to French, in which a hybrid approach of query and document translation was attempted, i.e, combining results of query translation (German to French) and of document translation (French to German). In order to avoid too high complexity of computation for translating a large amount of texts in documents, we executed pseudo-translation, i.e., a simple replacement of terms by a bilingual dictionary (for query translation, a machine translation system was used). In particular, since English was used as an intermediary language for both translation directions of German and French, English translations at the middle stage were employed as document representations in order to reduce the number of translation steps. By omitting a translation step (English to German), the performance was improved. Unfortunately, our hybrid approach could not show better performance than a simple query translation. This may be due to the low performance of document translation, which was carried out by a simple replacement of terms using a bilingual dictionary with no term disambiguation.

KW - Cross-language information retrieval

KW - Document translation

KW - Hybrid approach

KW - Query translation

UR - http://www.scopus.com/inward/record.url?scp=84922022132&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922022132&partnerID=8YFLogxK

M3 - Conference contribution

VL - 1171

BT - CEUR Workshop Proceedings

PB - CEUR-WS

ER -