@inproceedings{tan-etal-2023-multilingual,
title = "Multilingual Representation Distillation with Contrastive Learning",
author = "Tan, Weiting and
Heffernan, Kevin and
Schwenk, Holger and
Koehn, Philipp",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.108",
doi = "10.18653/v1/2023.eacl-main.108",
pages = "1477--1490",
abstract = "Multilingual sentence representations from large models encode semantic information from two or more languages and can be used for different cross-lingual information retrieval and matching tasks. In this paper, we integrate contrastive learning into multilingual representation distillation and use it for quality estimation of parallel sentences (i.e., find semantically similar sentences that can be used as translations of each other). We validate our approach with multilingual similarity search and corpus filtering tasks. Experiments across different low-resource languages show that our method greatly outperforms previous sentence encoders such as LASER, LASER3, and LaBSE.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tan-etal-2023-multilingual">
<titleInfo>
<title>Multilingual Representation Distillation with Contrastive Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weiting</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Heffernan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Holger</namePart>
<namePart type="family">Schwenk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multilingual sentence representations from large models encode semantic information from two or more languages and can be used for different cross-lingual information retrieval and matching tasks. In this paper, we integrate contrastive learning into multilingual representation distillation and use it for quality estimation of parallel sentences (i.e., find semantically similar sentences that can be used as translations of each other). We validate our approach with multilingual similarity search and corpus filtering tasks. Experiments across different low-resource languages show that our method greatly outperforms previous sentence encoders such as LASER, LASER3, and LaBSE.</abstract>
<identifier type="citekey">tan-etal-2023-multilingual</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.108</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.108</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>1477</start>
<end>1490</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual Representation Distillation with Contrastive Learning
%A Tan, Weiting
%A Heffernan, Kevin
%A Schwenk, Holger
%A Koehn, Philipp
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F tan-etal-2023-multilingual
%X Multilingual sentence representations from large models encode semantic information from two or more languages and can be used for different cross-lingual information retrieval and matching tasks. In this paper, we integrate contrastive learning into multilingual representation distillation and use it for quality estimation of parallel sentences (i.e., find semantically similar sentences that can be used as translations of each other). We validate our approach with multilingual similarity search and corpus filtering tasks. Experiments across different low-resource languages show that our method greatly outperforms previous sentence encoders such as LASER, LASER3, and LaBSE.
%R 10.18653/v1/2023.eacl-main.108
%U https://aclanthology.org/2023.eacl-main.108
%U https://doi.org/10.18653/v1/2023.eacl-main.108
%P 1477-1490
Markdown (Informal)
[Multilingual Representation Distillation with Contrastive Learning](https://aclanthology.org/2023.eacl-main.108) (Tan et al., EACL 2023)
ACL
- Weiting Tan, Kevin Heffernan, Holger Schwenk, and Philipp Koehn. 2023. Multilingual Representation Distillation with Contrastive Learning. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 1477–1490, Dubrovnik, Croatia. Association for Computational Linguistics.