@inproceedings{gao-etal-2023-improving,
title = "Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization",
author = "Gao, Pengzhi and
Zhang, Liwen and
He, Zhongjun and
Wu, Hua and
Wang, Haifeng",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.766",
doi = "10.18653/v1/2023.findings-acl.766",
pages = "12103--12119",
abstract = "The multilingual neural machine translation (NMT) model has a promising capability of zero-shot translation, where it could directly translate between language pairs unseen during training. For good transfer performance from supervised directions to zero-shot directions, the multilingual NMT model is expected to learn universal representations across different languages. This paper introduces a cross-lingual consistency regularization, CrossConST, to bridge the representation gap among different languages and boost zero-shot translation performance. The theoretical analysis shows that CrossConST implicitly maximizes the probability distribution for zero-shot translation, and the experimental results on both low-resource and high-resource benchmarks show that CrossConST consistently improves the translation performance. The experimental analysis also proves that CrossConST could close the sentence representation gap and better align the representation space. Given the universality and simplicity of CrossConST, we believe it can serve as a strong baseline for future multilingual NMT research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gao-etal-2023-improving">
<titleInfo>
<title>Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pengzhi</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liwen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongjun</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haifeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The multilingual neural machine translation (NMT) model has a promising capability of zero-shot translation, where it could directly translate between language pairs unseen during training. For good transfer performance from supervised directions to zero-shot directions, the multilingual NMT model is expected to learn universal representations across different languages. This paper introduces a cross-lingual consistency regularization, CrossConST, to bridge the representation gap among different languages and boost zero-shot translation performance. The theoretical analysis shows that CrossConST implicitly maximizes the probability distribution for zero-shot translation, and the experimental results on both low-resource and high-resource benchmarks show that CrossConST consistently improves the translation performance. The experimental analysis also proves that CrossConST could close the sentence representation gap and better align the representation space. Given the universality and simplicity of CrossConST, we believe it can serve as a strong baseline for future multilingual NMT research.</abstract>
<identifier type="citekey">gao-etal-2023-improving</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.766</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.766</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>12103</start>
<end>12119</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization
%A Gao, Pengzhi
%A Zhang, Liwen
%A He, Zhongjun
%A Wu, Hua
%A Wang, Haifeng
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F gao-etal-2023-improving
%X The multilingual neural machine translation (NMT) model has a promising capability of zero-shot translation, where it could directly translate between language pairs unseen during training. For good transfer performance from supervised directions to zero-shot directions, the multilingual NMT model is expected to learn universal representations across different languages. This paper introduces a cross-lingual consistency regularization, CrossConST, to bridge the representation gap among different languages and boost zero-shot translation performance. The theoretical analysis shows that CrossConST implicitly maximizes the probability distribution for zero-shot translation, and the experimental results on both low-resource and high-resource benchmarks show that CrossConST consistently improves the translation performance. The experimental analysis also proves that CrossConST could close the sentence representation gap and better align the representation space. Given the universality and simplicity of CrossConST, we believe it can serve as a strong baseline for future multilingual NMT research.
%R 10.18653/v1/2023.findings-acl.766
%U https://aclanthology.org/2023.findings-acl.766
%U https://doi.org/10.18653/v1/2023.findings-acl.766
%P 12103-12119
Markdown (Informal)
[Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization](https://aclanthology.org/2023.findings-acl.766) (Gao et al., Findings 2023)
ACL