Adaptation of the translation model for statistical machine translation based on information retrieval

Almut Silja Hildebrand, Matthias Eck, Stephan Vogel, Alex Waibel

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

70 Citations (Scopus)

Abstract

In this paper we present experiments concerning translation model adaptation for statistical machine translation. We develop a method to adapt translation models using information retrieval. The approach selects sentences similar to the test set to form an adapted training corpus. The method allows a better use of additionally available out-of-domain training data or finds in-domain data in a mixed corpus. The adapted translation models significantly improve the translation performance compared to competitive baseline systems.

Original languageEnglish
Title of host publicationEuropean Association for Machine Translation, EAMT 2005 - 10th Annual Conference
Pages133-142
Number of pages10
Publication statusPublished - 1 Dec 2005
Externally publishedYes
Event10th Annual Conference on European Association for Machine Translation, EAMT 2005 - Budapest, Hungary
Duration: 30 May 200531 May 2005

Other

Other10th Annual Conference on European Association for Machine Translation, EAMT 2005
CountryHungary
CityBudapest
Period30/5/0531/5/05

Fingerprint

Information retrieval
Statistical Machine Translation
Information Retrieval
Experiments

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Software

Cite this

Hildebrand, A. S., Eck, M., Vogel, S., & Waibel, A. (2005). Adaptation of the translation model for statistical machine translation based on information retrieval. In European Association for Machine Translation, EAMT 2005 - 10th Annual Conference (pp. 133-142)

Adaptation of the translation model for statistical machine translation based on information retrieval. / Hildebrand, Almut Silja; Eck, Matthias; Vogel, Stephan; Waibel, Alex.

European Association for Machine Translation, EAMT 2005 - 10th Annual Conference. 2005. p. 133-142.

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

Hildebrand, AS, Eck, M, Vogel, S & Waibel, A 2005, Adaptation of the translation model for statistical machine translation based on information retrieval. in European Association for Machine Translation, EAMT 2005 - 10th Annual Conference. pp. 133-142, 10th Annual Conference on European Association for Machine Translation, EAMT 2005, Budapest, Hungary, 30/5/05.
Hildebrand AS, Eck M, Vogel S, Waibel A. Adaptation of the translation model for statistical machine translation based on information retrieval. In European Association for Machine Translation, EAMT 2005 - 10th Annual Conference. 2005. p. 133-142
Hildebrand, Almut Silja ; Eck, Matthias ; Vogel, Stephan ; Waibel, Alex. / Adaptation of the translation model for statistical machine translation based on information retrieval. European Association for Machine Translation, EAMT 2005 - 10th Annual Conference. 2005. pp. 133-142
@inproceedings{9479fec84d274088b659c9a09d26bb36,
title = "Adaptation of the translation model for statistical machine translation based on information retrieval",
abstract = "In this paper we present experiments concerning translation model adaptation for statistical machine translation. We develop a method to adapt translation models using information retrieval. The approach selects sentences similar to the test set to form an adapted training corpus. The method allows a better use of additionally available out-of-domain training data or finds in-domain data in a mixed corpus. The adapted translation models significantly improve the translation performance compared to competitive baseline systems.",
author = "Hildebrand, {Almut Silja} and Matthias Eck and Stephan Vogel and Alex Waibel",
year = "2005",
month = "12",
day = "1",
language = "English",
pages = "133--142",
booktitle = "European Association for Machine Translation, EAMT 2005 - 10th Annual Conference",

}

TY - GEN

T1 - Adaptation of the translation model for statistical machine translation based on information retrieval

AU - Hildebrand, Almut Silja

AU - Eck, Matthias

AU - Vogel, Stephan

AU - Waibel, Alex

PY - 2005/12/1

Y1 - 2005/12/1

N2 - In this paper we present experiments concerning translation model adaptation for statistical machine translation. We develop a method to adapt translation models using information retrieval. The approach selects sentences similar to the test set to form an adapted training corpus. The method allows a better use of additionally available out-of-domain training data or finds in-domain data in a mixed corpus. The adapted translation models significantly improve the translation performance compared to competitive baseline systems.

AB - In this paper we present experiments concerning translation model adaptation for statistical machine translation. We develop a method to adapt translation models using information retrieval. The approach selects sentences similar to the test set to form an adapted training corpus. The method allows a better use of additionally available out-of-domain training data or finds in-domain data in a mixed corpus. The adapted translation models significantly improve the translation performance compared to competitive baseline systems.

UR - http://www.scopus.com/inward/record.url?scp=84857591265&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84857591265&partnerID=8YFLogxK

M3 - Conference contribution

SP - 133

EP - 142

BT - European Association for Machine Translation, EAMT 2005 - 10th Annual Conference

ER -