@inproceedings{xu-etal-2021-bilingual,
title = "Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation",
author = "Xu, Yangyifan and
Liu, Yijin and
Meng, Fandong and
Zhang, Jiajun and
Xu, Jinan and
Zhou, Jie",
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 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.65",
doi = "10.18653/v1/2021.acl-short.65",
pages = "511--516",
abstract = "Recently, token-level adaptive training has achieved promising improvement in machine translation, where the cross-entropy loss function is adjusted by assigning different training weights to different tokens, in order to alleviate the token imbalance problem. However, previous approaches only use static word frequency information in the target language without considering the source language, which is insufficient for bilingual tasks like machine translation. In this paper, we propose a novel bilingual mutual information (BMI) based adaptive objective, which measures the learning difficulty for each target token from the perspective of bilingualism, and assigns an adaptive weight accordingly to improve token-level adaptive training. This method assigns larger training weights to tokens with higher BMI, so that easy tokens are updated with coarse granularity while difficult tokens are updated with fine granularity. Experimental results on WMT14 English-to-German and WMT19 Chinese-to-English demonstrate the superiority of our approach compared with the Transformer baseline and previous token-level adaptive training approaches. Further analyses confirm that our method can improve the lexical diversity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2021-bilingual">
<titleInfo>
<title>Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yangyifan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yijin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fandong</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Zhou</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 2: Short 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>Recently, token-level adaptive training has achieved promising improvement in machine translation, where the cross-entropy loss function is adjusted by assigning different training weights to different tokens, in order to alleviate the token imbalance problem. However, previous approaches only use static word frequency information in the target language without considering the source language, which is insufficient for bilingual tasks like machine translation. In this paper, we propose a novel bilingual mutual information (BMI) based adaptive objective, which measures the learning difficulty for each target token from the perspective of bilingualism, and assigns an adaptive weight accordingly to improve token-level adaptive training. This method assigns larger training weights to tokens with higher BMI, so that easy tokens are updated with coarse granularity while difficult tokens are updated with fine granularity. Experimental results on WMT14 English-to-German and WMT19 Chinese-to-English demonstrate the superiority of our approach compared with the Transformer baseline and previous token-level adaptive training approaches. Further analyses confirm that our method can improve the lexical diversity.</abstract>
<identifier type="citekey">xu-etal-2021-bilingual</identifier>
<identifier type="doi">10.18653/v1/2021.acl-short.65</identifier>
<location>
<url>https://aclanthology.org/2021.acl-short.65</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>511</start>
<end>516</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation
%A Xu, Yangyifan
%A Liu, Yijin
%A Meng, Fandong
%A Zhang, Jiajun
%A Xu, Jinan
%A Zhou, Jie
%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 2: Short Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F xu-etal-2021-bilingual
%X Recently, token-level adaptive training has achieved promising improvement in machine translation, where the cross-entropy loss function is adjusted by assigning different training weights to different tokens, in order to alleviate the token imbalance problem. However, previous approaches only use static word frequency information in the target language without considering the source language, which is insufficient for bilingual tasks like machine translation. In this paper, we propose a novel bilingual mutual information (BMI) based adaptive objective, which measures the learning difficulty for each target token from the perspective of bilingualism, and assigns an adaptive weight accordingly to improve token-level adaptive training. This method assigns larger training weights to tokens with higher BMI, so that easy tokens are updated with coarse granularity while difficult tokens are updated with fine granularity. Experimental results on WMT14 English-to-German and WMT19 Chinese-to-English demonstrate the superiority of our approach compared with the Transformer baseline and previous token-level adaptive training approaches. Further analyses confirm that our method can improve the lexical diversity.
%R 10.18653/v1/2021.acl-short.65
%U https://aclanthology.org/2021.acl-short.65
%U https://doi.org/10.18653/v1/2021.acl-short.65
%P 511-516
Markdown (Informal)
[Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation](https://aclanthology.org/2021.acl-short.65) (Xu et al., ACL-IJCNLP 2021)
ACL
- Yangyifan Xu, Yijin Liu, Fandong Meng, Jiajun Zhang, Jinan Xu, and Jie Zhou. 2021. Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 511–516, Online. Association for Computational Linguistics.