@inproceedings{laville-etal-2020-data,
title = "Data Selection for Bilingual Lexicon Induction from Specialized Comparable Corpora",
author = "Laville, Martin and
Hazem, Amir and
Morin, Emmanuel and
Langlais, Phillippe",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.527/",
doi = "10.18653/v1/2020.coling-main.527",
pages = "6002--6012",
abstract = "Narrow specialized comparable corpora are often small in size. This particularity makes it difficult to build efficient models to acquire translation equivalents, especially for less frequent and rare words. One way to overcome this issue is to enrich the specialized corpora with out-of-domain resources. Although some recent studies have shown improvements using data augmentation, the enrichment method was roughly conducted by adding out-of-domain data with no particular attention given to how to enrich words and how to do it optimally. In this paper, we contrast several data selection techniques to improve bilingual lexicon induction from specialized comparable corpora. We first apply two well-established data selection techniques often used in machine translation that is: Tf-Idf and cross entropy. Then, we propose to exploit BERT for data selection. Overall, all the proposed techniques improve the quality of the extracted bilingual lexicons by a large margin. The best performing model is the cross entropy, obtaining a gain of about 4 points in MAP while decreasing computation time by a factor of 10."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="laville-etal-2020-data">
<titleInfo>
<title>Data Selection for Bilingual Lexicon Induction from Specialized Comparable Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Laville</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Hazem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuel</namePart>
<namePart type="family">Morin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phillippe</namePart>
<namePart type="family">Langlais</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Narrow specialized comparable corpora are often small in size. This particularity makes it difficult to build efficient models to acquire translation equivalents, especially for less frequent and rare words. One way to overcome this issue is to enrich the specialized corpora with out-of-domain resources. Although some recent studies have shown improvements using data augmentation, the enrichment method was roughly conducted by adding out-of-domain data with no particular attention given to how to enrich words and how to do it optimally. In this paper, we contrast several data selection techniques to improve bilingual lexicon induction from specialized comparable corpora. We first apply two well-established data selection techniques often used in machine translation that is: Tf-Idf and cross entropy. Then, we propose to exploit BERT for data selection. Overall, all the proposed techniques improve the quality of the extracted bilingual lexicons by a large margin. The best performing model is the cross entropy, obtaining a gain of about 4 points in MAP while decreasing computation time by a factor of 10.</abstract>
<identifier type="citekey">laville-etal-2020-data</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.527</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.527/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>6002</start>
<end>6012</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Selection for Bilingual Lexicon Induction from Specialized Comparable Corpora
%A Laville, Martin
%A Hazem, Amir
%A Morin, Emmanuel
%A Langlais, Phillippe
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F laville-etal-2020-data
%X Narrow specialized comparable corpora are often small in size. This particularity makes it difficult to build efficient models to acquire translation equivalents, especially for less frequent and rare words. One way to overcome this issue is to enrich the specialized corpora with out-of-domain resources. Although some recent studies have shown improvements using data augmentation, the enrichment method was roughly conducted by adding out-of-domain data with no particular attention given to how to enrich words and how to do it optimally. In this paper, we contrast several data selection techniques to improve bilingual lexicon induction from specialized comparable corpora. We first apply two well-established data selection techniques often used in machine translation that is: Tf-Idf and cross entropy. Then, we propose to exploit BERT for data selection. Overall, all the proposed techniques improve the quality of the extracted bilingual lexicons by a large margin. The best performing model is the cross entropy, obtaining a gain of about 4 points in MAP while decreasing computation time by a factor of 10.
%R 10.18653/v1/2020.coling-main.527
%U https://aclanthology.org/2020.coling-main.527/
%U https://doi.org/10.18653/v1/2020.coling-main.527
%P 6002-6012
Markdown (Informal)
[Data Selection for Bilingual Lexicon Induction from Specialized Comparable Corpora](https://aclanthology.org/2020.coling-main.527/) (Laville et al., COLING 2020)
ACL