@inproceedings{park-etal-2024-improving-multi,
title = "Improving Multi-lingual Alignment Through Soft Contrastive Learning",
author = "Park, Minsu and
Choi, Seyeon and
Choi, Chanyeol and
Kim, Jun-Seong and
Sohn, Jy-yong",
editor = "Cao, Yang (Trista) and
Papadimitriou, Isabel and
Ovalle, Anaelia and
Zampieri, Marcos and
Ferraro, Francis and
Swayamdipta, Swabha",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-srw.16",
doi = "10.18653/v1/2024.naacl-srw.16",
pages = "138--145",
abstract = "Making decent multi-lingual sentence representations is critical to achieve high performances in cross-lingual downstream tasks. In this work, we propose a novel method to align multi-lingual embeddings based on the similarity of sentences measured by a pre-trained mono-lingual embedding model. Given translation sentence pairs, we train a multi-lingual model in a way that the similarity between cross-lingual embeddings follows the similarity of sentences measured at the mono-lingual teacher model. Our method can be considered as contrastive learning with soft labels defined as the similarity between sentences. Our experimental results on five languages show that our contrastive loss with soft labels far outperforms conventional constrastive loss with hard labels in various benchmarks for bitext mining tasks and STS tasks. In addition, our method outperforms existing multi-lingual embeddings including LaBSE, for Tatoeba dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2024-improving-multi">
<titleInfo>
<title>Improving Multi-lingual Alignment Through Soft Contrastive Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minsu</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seyeon</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chanyeol</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun-Seong</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jy-yong</namePart>
<namePart type="family">Sohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="given">(Trista)</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Papadimitriou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaelia</namePart>
<namePart type="family">Ovalle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Ferraro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Making decent multi-lingual sentence representations is critical to achieve high performances in cross-lingual downstream tasks. In this work, we propose a novel method to align multi-lingual embeddings based on the similarity of sentences measured by a pre-trained mono-lingual embedding model. Given translation sentence pairs, we train a multi-lingual model in a way that the similarity between cross-lingual embeddings follows the similarity of sentences measured at the mono-lingual teacher model. Our method can be considered as contrastive learning with soft labels defined as the similarity between sentences. Our experimental results on five languages show that our contrastive loss with soft labels far outperforms conventional constrastive loss with hard labels in various benchmarks for bitext mining tasks and STS tasks. In addition, our method outperforms existing multi-lingual embeddings including LaBSE, for Tatoeba dataset.</abstract>
<identifier type="citekey">park-etal-2024-improving-multi</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-srw.16</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-srw.16</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>138</start>
<end>145</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Multi-lingual Alignment Through Soft Contrastive Learning
%A Park, Minsu
%A Choi, Seyeon
%A Choi, Chanyeol
%A Kim, Jun-Seong
%A Sohn, Jy-yong
%Y Cao, Yang (Trista)
%Y Papadimitriou, Isabel
%Y Ovalle, Anaelia
%Y Zampieri, Marcos
%Y Ferraro, Francis
%Y Swayamdipta, Swabha
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F park-etal-2024-improving-multi
%X Making decent multi-lingual sentence representations is critical to achieve high performances in cross-lingual downstream tasks. In this work, we propose a novel method to align multi-lingual embeddings based on the similarity of sentences measured by a pre-trained mono-lingual embedding model. Given translation sentence pairs, we train a multi-lingual model in a way that the similarity between cross-lingual embeddings follows the similarity of sentences measured at the mono-lingual teacher model. Our method can be considered as contrastive learning with soft labels defined as the similarity between sentences. Our experimental results on five languages show that our contrastive loss with soft labels far outperforms conventional constrastive loss with hard labels in various benchmarks for bitext mining tasks and STS tasks. In addition, our method outperforms existing multi-lingual embeddings including LaBSE, for Tatoeba dataset.
%R 10.18653/v1/2024.naacl-srw.16
%U https://aclanthology.org/2024.naacl-srw.16
%U https://doi.org/10.18653/v1/2024.naacl-srw.16
%P 138-145
Markdown (Informal)
[Improving Multi-lingual Alignment Through Soft Contrastive Learning](https://aclanthology.org/2024.naacl-srw.16) (Park et al., NAACL 2024)
ACL
- Minsu Park, Seyeon Choi, Chanyeol Choi, Jun-Seong Kim, and Jy-yong Sohn. 2024. Improving Multi-lingual Alignment Through Soft Contrastive Learning. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pages 138–145, Mexico City, Mexico. Association for Computational Linguistics.