@inproceedings{li-etal-2021-miss-wmt21,
title = "{M}i{SS}@{WMT}21: Contrastive Learning-reinforced Domain Adaptation in Neural Machine Translation",
author = "Li, Zuchao and
Utiyama, Masao and
Sumita, Eiichiro and
Zhao, Hai",
booktitle = "Proceedings of the Sixth Conference on Machine Translation",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wmt-1.12",
pages = "154--161",
abstract = "In this paper, we describe our MiSS system that participated in the WMT21 news translation task. We mainly participated in the evaluation of the three translation directions of English-Chinese and Japanese-English translation tasks. In the systems submitted, we primarily considered wider networks, deeper networks, relative positional encoding, and dynamic convolutional networks in terms of model structure, while in terms of training, we investigated contrastive learning-reinforced domain adaptation, self-supervised training, and optimization objective switching training methods. According to the final evaluation results, a deeper, wider, and stronger network can improve translation performance in general, yet our data domain adaption method can improve performance even more. In addition, we found that switching to the use of our proposed objective during the finetune phase using relatively small domain-related data can effectively improve the stability of the model{'}s convergence and achieve better optimal performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2021-miss-wmt21">
<titleInfo>
<title>MiSS@WMT21: Contrastive Learning-reinforced Domain Adaptation in Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zuchao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiichiro</namePart>
<namePart type="family">Sumita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hai</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Conference on Machine Translation</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe our MiSS system that participated in the WMT21 news translation task. We mainly participated in the evaluation of the three translation directions of English-Chinese and Japanese-English translation tasks. In the systems submitted, we primarily considered wider networks, deeper networks, relative positional encoding, and dynamic convolutional networks in terms of model structure, while in terms of training, we investigated contrastive learning-reinforced domain adaptation, self-supervised training, and optimization objective switching training methods. According to the final evaluation results, a deeper, wider, and stronger network can improve translation performance in general, yet our data domain adaption method can improve performance even more. In addition, we found that switching to the use of our proposed objective during the finetune phase using relatively small domain-related data can effectively improve the stability of the model’s convergence and achieve better optimal performance.</abstract>
<identifier type="citekey">li-etal-2021-miss-wmt21</identifier>
<location>
<url>https://aclanthology.org/2021.wmt-1.12</url>
</location>
<part>
<date>2021-nov</date>
<extent unit="page">
<start>154</start>
<end>161</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MiSS@WMT21: Contrastive Learning-reinforced Domain Adaptation in Neural Machine Translation
%A Li, Zuchao
%A Utiyama, Masao
%A Sumita, Eiichiro
%A Zhao, Hai
%S Proceedings of the Sixth Conference on Machine Translation
%D 2021
%8 nov
%I Association for Computational Linguistics
%C Online
%F li-etal-2021-miss-wmt21
%X In this paper, we describe our MiSS system that participated in the WMT21 news translation task. We mainly participated in the evaluation of the three translation directions of English-Chinese and Japanese-English translation tasks. In the systems submitted, we primarily considered wider networks, deeper networks, relative positional encoding, and dynamic convolutional networks in terms of model structure, while in terms of training, we investigated contrastive learning-reinforced domain adaptation, self-supervised training, and optimization objective switching training methods. According to the final evaluation results, a deeper, wider, and stronger network can improve translation performance in general, yet our data domain adaption method can improve performance even more. In addition, we found that switching to the use of our proposed objective during the finetune phase using relatively small domain-related data can effectively improve the stability of the model’s convergence and achieve better optimal performance.
%U https://aclanthology.org/2021.wmt-1.12
%P 154-161
Markdown (Informal)
[MiSS@WMT21: Contrastive Learning-reinforced Domain Adaptation in Neural Machine Translation](https://aclanthology.org/2021.wmt-1.12) (Li et al., WMT 2021)
ACL