@inproceedings{wu-etal-2019-extract,
title = "Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation",
author = "Wu, Jiawei and
Wang, Xin and
Wang, William Yang",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1120",
doi = "10.18653/v1/N19-1120",
pages = "1173--1183",
abstract = "The overreliance on large parallel corpora significantly limits the applicability of machine translation systems to the majority of language pairs. Back-translation has been dominantly used in previous approaches for unsupervised neural machine translation, where pseudo sentence pairs are generated to train the models with a reconstruction loss. However, the pseudo sentences are usually of low quality as translation errors accumulate during training. To avoid this fundamental issue, we propose an alternative but more effective approach, extract-edit, to extract and then edit real sentences from the target monolingual corpora. Furthermore, we introduce a comparative translation loss to evaluate the translated target sentences and thus train the unsupervised translation systems. Experiments show that the proposed approach consistently outperforms the previous state-of-the-art unsupervised machine translation systems across two benchmarks (English-French and English-German) and two low-resource language pairs (English-Romanian and English-Russian) by more than 2 (up to 3.63) BLEU points.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2019-extract">
<titleInfo>
<title>Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="given">Yang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The overreliance on large parallel corpora significantly limits the applicability of machine translation systems to the majority of language pairs. Back-translation has been dominantly used in previous approaches for unsupervised neural machine translation, where pseudo sentence pairs are generated to train the models with a reconstruction loss. However, the pseudo sentences are usually of low quality as translation errors accumulate during training. To avoid this fundamental issue, we propose an alternative but more effective approach, extract-edit, to extract and then edit real sentences from the target monolingual corpora. Furthermore, we introduce a comparative translation loss to evaluate the translated target sentences and thus train the unsupervised translation systems. Experiments show that the proposed approach consistently outperforms the previous state-of-the-art unsupervised machine translation systems across two benchmarks (English-French and English-German) and two low-resource language pairs (English-Romanian and English-Russian) by more than 2 (up to 3.63) BLEU points.</abstract>
<identifier type="citekey">wu-etal-2019-extract</identifier>
<identifier type="doi">10.18653/v1/N19-1120</identifier>
<location>
<url>https://aclanthology.org/N19-1120</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>1173</start>
<end>1183</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation
%A Wu, Jiawei
%A Wang, Xin
%A Wang, William Yang
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F wu-etal-2019-extract
%X The overreliance on large parallel corpora significantly limits the applicability of machine translation systems to the majority of language pairs. Back-translation has been dominantly used in previous approaches for unsupervised neural machine translation, where pseudo sentence pairs are generated to train the models with a reconstruction loss. However, the pseudo sentences are usually of low quality as translation errors accumulate during training. To avoid this fundamental issue, we propose an alternative but more effective approach, extract-edit, to extract and then edit real sentences from the target monolingual corpora. Furthermore, we introduce a comparative translation loss to evaluate the translated target sentences and thus train the unsupervised translation systems. Experiments show that the proposed approach consistently outperforms the previous state-of-the-art unsupervised machine translation systems across two benchmarks (English-French and English-German) and two low-resource language pairs (English-Romanian and English-Russian) by more than 2 (up to 3.63) BLEU points.
%R 10.18653/v1/N19-1120
%U https://aclanthology.org/N19-1120
%U https://doi.org/10.18653/v1/N19-1120
%P 1173-1183
Markdown (Informal)
[Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation](https://aclanthology.org/N19-1120) (Wu et al., NAACL 2019)
ACL