Multilingual alignments by monolingual string differences

Adrien Lardilleux, Yves Lepage

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

1 Citation (Scopus)

Abstract

We propose a method to obtain subsentential alignments from several languages simultaneously. The method handles several languages at once, and avoids the complexity explosion due to the usual pair-by-pair processing. It can be used for different units (characters, morphemes, words, chunks). An evaluation of word alignments with a trilingual machine translation corpus has been conducted. A comparison of the results with those obtained by state of the art alignment software is reported.

Original languageEnglish
Title of host publicationColing 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference
Pages55-58
Number of pages4
Volume1
Publication statusPublished - 2008
Externally publishedYes
Event22nd International Conference on Computational Linguistics, Coling 2008 - Manchester
Duration: 2008 Aug 182008 Aug 22

Other

Other22nd International Conference on Computational Linguistics, Coling 2008
CityManchester
Period08/8/1808/8/22

Fingerprint

language
Explosions
evaluation
Processing
Strings
Alignment
Language
software
Evaluation
Morpheme
Software
Translation Corpora
Machine Translation
Chunk

ASJC Scopus subject areas

  • Language and Linguistics
  • Computational Theory and Mathematics
  • Linguistics and Language

Cite this

Lardilleux, A., & Lepage, Y. (2008). Multilingual alignments by monolingual string differences. In Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference (Vol. 1, pp. 55-58)

Multilingual alignments by monolingual string differences. / Lardilleux, Adrien; Lepage, Yves.

Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference. Vol. 1 2008. p. 55-58.

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

Lardilleux, A & Lepage, Y 2008, Multilingual alignments by monolingual string differences. in Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference. vol. 1, pp. 55-58, 22nd International Conference on Computational Linguistics, Coling 2008, Manchester, 08/8/18.
Lardilleux A, Lepage Y. Multilingual alignments by monolingual string differences. In Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference. Vol. 1. 2008. p. 55-58
Lardilleux, Adrien ; Lepage, Yves. / Multilingual alignments by monolingual string differences. Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference. Vol. 1 2008. pp. 55-58
@inproceedings{18a05554a22b4f11887f8de74b60c4fe,
title = "Multilingual alignments by monolingual string differences",
abstract = "We propose a method to obtain subsentential alignments from several languages simultaneously. The method handles several languages at once, and avoids the complexity explosion due to the usual pair-by-pair processing. It can be used for different units (characters, morphemes, words, chunks). An evaluation of word alignments with a trilingual machine translation corpus has been conducted. A comparison of the results with those obtained by state of the art alignment software is reported.",
author = "Adrien Lardilleux and Yves Lepage",
year = "2008",
language = "English",
isbn = "9781905593446",
volume = "1",
pages = "55--58",
booktitle = "Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference",

}

TY - GEN

T1 - Multilingual alignments by monolingual string differences

AU - Lardilleux, Adrien

AU - Lepage, Yves

PY - 2008

Y1 - 2008

N2 - We propose a method to obtain subsentential alignments from several languages simultaneously. The method handles several languages at once, and avoids the complexity explosion due to the usual pair-by-pair processing. It can be used for different units (characters, morphemes, words, chunks). An evaluation of word alignments with a trilingual machine translation corpus has been conducted. A comparison of the results with those obtained by state of the art alignment software is reported.

AB - We propose a method to obtain subsentential alignments from several languages simultaneously. The method handles several languages at once, and avoids the complexity explosion due to the usual pair-by-pair processing. It can be used for different units (characters, morphemes, words, chunks). An evaluation of word alignments with a trilingual machine translation corpus has been conducted. A comparison of the results with those obtained by state of the art alignment software is reported.

UR - http://www.scopus.com/inward/record.url?scp=80053422840&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053422840&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781905593446

VL - 1

SP - 55

EP - 58

BT - Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference

ER -