@inproceedings{shi-etal-2021-bilingual,
title = "Bilingual Lexicon Induction via Unsupervised Bitext Construction and Word Alignment",
author = "Shi, Haoyue and
Zettlemoyer, Luke and
Wang, Sida I.",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.67/",
doi = "10.18653/v1/2021.acl-long.67",
pages = "813--826",
abstract = "Bilingual lexicons map words in one language to their translations in another, and are typically induced by learning linear projections to align monolingual word embedding spaces. In this paper, we show it is possible to produce much higher quality lexicons with methods that combine (1) unsupervised bitext mining and (2) unsupervised word alignment. Directly applying a pipeline that uses recent algorithms for both subproblems significantly improves induced lexicon quality and further gains are possible by learning to filter the resulting lexical entries, with both unsupervised and semi-supervised schemes. Our final model outperforms the state of the art on the BUCC 2020 shared task by 14 F1 points averaged over 12 language pairs, while also providing a more interpretable approach that allows for rich reasoning of word meaning in context. Further analysis of our output and the standard reference lexicons suggests they are of comparable quality, and new benchmarks may be needed to measure further progress on this task."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2021-bilingual">
<titleInfo>
<title>Bilingual Lexicon Induction via Unsupervised Bitext Construction and Word Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haoyue</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sida</namePart>
<namePart type="given">I</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Bilingual lexicons map words in one language to their translations in another, and are typically induced by learning linear projections to align monolingual word embedding spaces. In this paper, we show it is possible to produce much higher quality lexicons with methods that combine (1) unsupervised bitext mining and (2) unsupervised word alignment. Directly applying a pipeline that uses recent algorithms for both subproblems significantly improves induced lexicon quality and further gains are possible by learning to filter the resulting lexical entries, with both unsupervised and semi-supervised schemes. Our final model outperforms the state of the art on the BUCC 2020 shared task by 14 F1 points averaged over 12 language pairs, while also providing a more interpretable approach that allows for rich reasoning of word meaning in context. Further analysis of our output and the standard reference lexicons suggests they are of comparable quality, and new benchmarks may be needed to measure further progress on this task.</abstract>
<identifier type="citekey">shi-etal-2021-bilingual</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.67</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.67/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>813</start>
<end>826</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bilingual Lexicon Induction via Unsupervised Bitext Construction and Word Alignment
%A Shi, Haoyue
%A Zettlemoyer, Luke
%A Wang, Sida I.
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F shi-etal-2021-bilingual
%X Bilingual lexicons map words in one language to their translations in another, and are typically induced by learning linear projections to align monolingual word embedding spaces. In this paper, we show it is possible to produce much higher quality lexicons with methods that combine (1) unsupervised bitext mining and (2) unsupervised word alignment. Directly applying a pipeline that uses recent algorithms for both subproblems significantly improves induced lexicon quality and further gains are possible by learning to filter the resulting lexical entries, with both unsupervised and semi-supervised schemes. Our final model outperforms the state of the art on the BUCC 2020 shared task by 14 F1 points averaged over 12 language pairs, while also providing a more interpretable approach that allows for rich reasoning of word meaning in context. Further analysis of our output and the standard reference lexicons suggests they are of comparable quality, and new benchmarks may be needed to measure further progress on this task.
%R 10.18653/v1/2021.acl-long.67
%U https://aclanthology.org/2021.acl-long.67/
%U https://doi.org/10.18653/v1/2021.acl-long.67
%P 813-826
Markdown (Informal)
[Bilingual Lexicon Induction via Unsupervised Bitext Construction and Word Alignment](https://aclanthology.org/2021.acl-long.67/) (Shi et al., ACL-IJCNLP 2021)
ACL