@inproceedings{xu-etal-2021-vocabulary,
title = "Vocabulary Learning via Optimal Transport for Neural Machine Translation",
author = "Xu, Jingjing and
Zhou, Hao and
Gan, Chun and
Zheng, Zaixiang and
Li, Lei",
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 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.571",
doi = "10.18653/v1/2021.acl-long.571",
pages = "7361--7373",
abstract = "The choice of token vocabulary affects the performance of machine translation. This paper aims to figure out what is a good vocabulary and whether we can find the optimal vocabulary without trial training. To answer these questions, we first provide an alternative understanding of vocabulary from the perspective of information theory. It motivates us to formulate the quest of vocabularization {--} finding the best token dictionary with a proper size {--} as an optimal transport (OT) problem. We propose VOLT, a simple and efficient solution without trial training. Empirical results show that VOLT beats widely-used vocabularies in diverse scenarios, including WMT-14 English-German translation, TED bilingual translation, and TED multilingual translation. For example, VOLT achieves 70{\%} vocabulary size reduction and 0.5 BLEU gain on English-German translation. Also, compared to BPE-search, VOLT reduces the search time from 384 GPU hours to 30 GPU hours on English-German translation. Codes are available at \url{https://github.com/Jingjing-NLP/VOLT}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2021-vocabulary">
<titleInfo>
<title>Vocabulary Learning via Optimal Transport for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jingjing</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chun</namePart>
<namePart type="family">Gan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaixiang</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Li</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 1: Long 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>The choice of token vocabulary affects the performance of machine translation. This paper aims to figure out what is a good vocabulary and whether we can find the optimal vocabulary without trial training. To answer these questions, we first provide an alternative understanding of vocabulary from the perspective of information theory. It motivates us to formulate the quest of vocabularization – finding the best token dictionary with a proper size – as an optimal transport (OT) problem. We propose VOLT, a simple and efficient solution without trial training. Empirical results show that VOLT beats widely-used vocabularies in diverse scenarios, including WMT-14 English-German translation, TED bilingual translation, and TED multilingual translation. For example, VOLT achieves 70% vocabulary size reduction and 0.5 BLEU gain on English-German translation. Also, compared to BPE-search, VOLT reduces the search time from 384 GPU hours to 30 GPU hours on English-German translation. Codes are available at https://github.com/Jingjing-NLP/VOLT.</abstract>
<identifier type="citekey">xu-etal-2021-vocabulary</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.571</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.571</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>7361</start>
<end>7373</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Vocabulary Learning via Optimal Transport for Neural Machine Translation
%A Xu, Jingjing
%A Zhou, Hao
%A Gan, Chun
%A Zheng, Zaixiang
%A Li, Lei
%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 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F xu-etal-2021-vocabulary
%X The choice of token vocabulary affects the performance of machine translation. This paper aims to figure out what is a good vocabulary and whether we can find the optimal vocabulary without trial training. To answer these questions, we first provide an alternative understanding of vocabulary from the perspective of information theory. It motivates us to formulate the quest of vocabularization – finding the best token dictionary with a proper size – as an optimal transport (OT) problem. We propose VOLT, a simple and efficient solution without trial training. Empirical results show that VOLT beats widely-used vocabularies in diverse scenarios, including WMT-14 English-German translation, TED bilingual translation, and TED multilingual translation. For example, VOLT achieves 70% vocabulary size reduction and 0.5 BLEU gain on English-German translation. Also, compared to BPE-search, VOLT reduces the search time from 384 GPU hours to 30 GPU hours on English-German translation. Codes are available at https://github.com/Jingjing-NLP/VOLT.
%R 10.18653/v1/2021.acl-long.571
%U https://aclanthology.org/2021.acl-long.571
%U https://doi.org/10.18653/v1/2021.acl-long.571
%P 7361-7373
Markdown (Informal)
[Vocabulary Learning via Optimal Transport for Neural Machine Translation](https://aclanthology.org/2021.acl-long.571) (Xu et al., ACL-IJCNLP 2021)
ACL
- Jingjing Xu, Hao Zhou, Chun Gan, Zaixiang Zheng, and Lei Li. 2021. Vocabulary Learning via Optimal Transport 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 1: Long Papers), pages 7361–7373, Online. Association for Computational Linguistics.