@inproceedings{deguchi-etal-2020-bilingual,
title = "Bilingual Subword Segmentation for Neural Machine Translation",
author = "Deguchi, Hiroyuki and
Utiyama, Masao and
Tamura, Akihiro and
Ninomiya, Takashi and
Sumita, Eiichiro",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.378/",
doi = "10.18653/v1/2020.coling-main.378",
pages = "4287--4297",
abstract = "This paper proposed a new subword segmentation method for neural machine translation, {\textquotedblleft}Bilingual Subword Segmentation,{\textquotedblright} which tokenizes sentences to minimize the difference between the number of subword units in a sentence and that of its translation. While existing subword segmentation methods tokenize a sentence without considering its translation, the proposed method tokenizes a sentence by using subword units induced from bilingual sentences; this method could be more favorable to machine translation. Evaluations on WAT Asian Scientific Paper Excerpt Corpus (ASPEC) English-to-Japanese and Japanese-to-English translation tasks and WMT14 English-to-German and German-to-English translation tasks show that our bilingual subword segmentation improves the performance of Transformer neural machine translation (up to +0.81 BLEU)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deguchi-etal-2020-bilingual">
<titleInfo>
<title>Bilingual Subword Segmentation for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hiroyuki</namePart>
<namePart type="family">Deguchi</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">Akihiro</namePart>
<namePart type="family">Tamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takashi</namePart>
<namePart type="family">Ninomiya</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>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper proposed a new subword segmentation method for neural machine translation, “Bilingual Subword Segmentation,” which tokenizes sentences to minimize the difference between the number of subword units in a sentence and that of its translation. While existing subword segmentation methods tokenize a sentence without considering its translation, the proposed method tokenizes a sentence by using subword units induced from bilingual sentences; this method could be more favorable to machine translation. Evaluations on WAT Asian Scientific Paper Excerpt Corpus (ASPEC) English-to-Japanese and Japanese-to-English translation tasks and WMT14 English-to-German and German-to-English translation tasks show that our bilingual subword segmentation improves the performance of Transformer neural machine translation (up to +0.81 BLEU).</abstract>
<identifier type="citekey">deguchi-etal-2020-bilingual</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.378</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.378/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>4287</start>
<end>4297</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bilingual Subword Segmentation for Neural Machine Translation
%A Deguchi, Hiroyuki
%A Utiyama, Masao
%A Tamura, Akihiro
%A Ninomiya, Takashi
%A Sumita, Eiichiro
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F deguchi-etal-2020-bilingual
%X This paper proposed a new subword segmentation method for neural machine translation, “Bilingual Subword Segmentation,” which tokenizes sentences to minimize the difference between the number of subword units in a sentence and that of its translation. While existing subword segmentation methods tokenize a sentence without considering its translation, the proposed method tokenizes a sentence by using subword units induced from bilingual sentences; this method could be more favorable to machine translation. Evaluations on WAT Asian Scientific Paper Excerpt Corpus (ASPEC) English-to-Japanese and Japanese-to-English translation tasks and WMT14 English-to-German and German-to-English translation tasks show that our bilingual subword segmentation improves the performance of Transformer neural machine translation (up to +0.81 BLEU).
%R 10.18653/v1/2020.coling-main.378
%U https://aclanthology.org/2020.coling-main.378/
%U https://doi.org/10.18653/v1/2020.coling-main.378
%P 4287-4297
Markdown (Informal)
[Bilingual Subword Segmentation for Neural Machine Translation](https://aclanthology.org/2020.coling-main.378/) (Deguchi et al., COLING 2020)
ACL
- Hiroyuki Deguchi, Masao Utiyama, Akihiro Tamura, Takashi Ninomiya, and Eiichiro Sumita. 2020. Bilingual Subword Segmentation for Neural Machine Translation. In Proceedings of the 28th International Conference on Computational Linguistics, pages 4287–4297, Barcelona, Spain (Online). International Committee on Computational Linguistics.