Sampling-based multilingual alignment

Adrien Lardilleux, Yves Lepage

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

27 Citations (Scopus)

Abstract

We present a sub-sentential alignment method that extracts high quality multi-word alignments from sentence-aligned multilingual parallel corpora. Unlike other methods, it exploits low frequency terms, which makes it highly scalable. As it relies on alingual concepts, it can process any number of languages at once. Experiments have shown that it is competitive with state-of-the-art methods.

Original languageEnglish
Title of host publicationInternational Conference Recent Advances in Natural Language Processing, RANLP
Pages214-218
Number of pages5
Publication statusPublished - 2009
Externally publishedYes
EventInternational Conference on Recent Advances in Natural Language Processing, RANLP-2009 - Borovets, Bulgaria
Duration: 2009 Sep 142009 Sep 16

Other

OtherInternational Conference on Recent Advances in Natural Language Processing, RANLP-2009
CountryBulgaria
CityBorovets
Period09/9/1409/9/16

Fingerprint

Sampling
Experiments

Keywords

  • Hapax
  • Low frequency term
  • Sampling
  • Sub-sentential alignment

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Software
  • Electrical and Electronic Engineering

Cite this

Lardilleux, A., & Lepage, Y. (2009). Sampling-based multilingual alignment. In International Conference Recent Advances in Natural Language Processing, RANLP (pp. 214-218)

Sampling-based multilingual alignment. / Lardilleux, Adrien; Lepage, Yves.

International Conference Recent Advances in Natural Language Processing, RANLP. 2009. p. 214-218.

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

Lardilleux, A & Lepage, Y 2009, Sampling-based multilingual alignment. in International Conference Recent Advances in Natural Language Processing, RANLP. pp. 214-218, International Conference on Recent Advances in Natural Language Processing, RANLP-2009, Borovets, Bulgaria, 09/9/14.
Lardilleux A, Lepage Y. Sampling-based multilingual alignment. In International Conference Recent Advances in Natural Language Processing, RANLP. 2009. p. 214-218
Lardilleux, Adrien ; Lepage, Yves. / Sampling-based multilingual alignment. International Conference Recent Advances in Natural Language Processing, RANLP. 2009. pp. 214-218
@inproceedings{c12c5b4e51cc44b6a8cb3e40ed498766,
title = "Sampling-based multilingual alignment",
abstract = "We present a sub-sentential alignment method that extracts high quality multi-word alignments from sentence-aligned multilingual parallel corpora. Unlike other methods, it exploits low frequency terms, which makes it highly scalable. As it relies on alingual concepts, it can process any number of languages at once. Experiments have shown that it is competitive with state-of-the-art methods.",
keywords = "Hapax, Low frequency term, Sampling, Sub-sentential alignment",
author = "Adrien Lardilleux and Yves Lepage",
year = "2009",
language = "English",
pages = "214--218",
booktitle = "International Conference Recent Advances in Natural Language Processing, RANLP",

}

TY - GEN

T1 - Sampling-based multilingual alignment

AU - Lardilleux, Adrien

AU - Lepage, Yves

PY - 2009

Y1 - 2009

N2 - We present a sub-sentential alignment method that extracts high quality multi-word alignments from sentence-aligned multilingual parallel corpora. Unlike other methods, it exploits low frequency terms, which makes it highly scalable. As it relies on alingual concepts, it can process any number of languages at once. Experiments have shown that it is competitive with state-of-the-art methods.

AB - We present a sub-sentential alignment method that extracts high quality multi-word alignments from sentence-aligned multilingual parallel corpora. Unlike other methods, it exploits low frequency terms, which makes it highly scalable. As it relies on alingual concepts, it can process any number of languages at once. Experiments have shown that it is competitive with state-of-the-art methods.

KW - Hapax

KW - Low frequency term

KW - Sampling

KW - Sub-sentential alignment

UR - http://www.scopus.com/inward/record.url?scp=80054830335&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80054830335&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:80054830335

SP - 214

EP - 218

BT - International Conference Recent Advances in Natural Language Processing, RANLP

ER -