@inproceedings{clinchant-etal-2019-use,
title = "On the use of {BERT} for Neural Machine Translation",
author = "Clinchant, Stephane and
Jung, Kweon Woo and
Nikoulina, Vassilina",
editor = "Birch, Alexandra and
Finch, Andrew and
Hayashi, Hiroaki and
Konstas, Ioannis and
Luong, Thang and
Neubig, Graham and
Oda, Yusuke and
Sudoh, Katsuhito",
booktitle = "Proceedings of the 3rd Workshop on Neural Generation and Translation",
month = nov,
year = "2019",
address = "Hong Kong",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-5611",
doi = "10.18653/v1/D19-5611",
pages = "108--117",
abstract = "Exploiting large pretrained models for various NMT tasks have gained a lot of visibility recently. In this work we study how BERT pretrained models could be exploited for supervised Neural Machine Translation. We compare various ways to integrate pretrained BERT model with NMT model and study the impact of the monolingual data used for BERT training on the final translation quality. We use WMT-14 English-German, IWSLT15 English-German and IWSLT14 English-Russian datasets for these experiments. In addition to standard task test set evaluation, we perform evaluation on out-of-domain test sets and noise injected test sets, in order to assess how BERT pretrained representations affect model robustness.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="clinchant-etal-2019-use">
<titleInfo>
<title>On the use of BERT for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stephane</namePart>
<namePart type="family">Clinchant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kweon</namePart>
<namePart type="given">Woo</namePart>
<namePart type="family">Jung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vassilina</namePart>
<namePart type="family">Nikoulina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Neural Generation and Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Birch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Finch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroaki</namePart>
<namePart type="family">Hayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioannis</namePart>
<namePart type="family">Konstas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thang</namePart>
<namePart type="family">Luong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Oda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katsuhito</namePart>
<namePart type="family">Sudoh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Exploiting large pretrained models for various NMT tasks have gained a lot of visibility recently. In this work we study how BERT pretrained models could be exploited for supervised Neural Machine Translation. We compare various ways to integrate pretrained BERT model with NMT model and study the impact of the monolingual data used for BERT training on the final translation quality. We use WMT-14 English-German, IWSLT15 English-German and IWSLT14 English-Russian datasets for these experiments. In addition to standard task test set evaluation, we perform evaluation on out-of-domain test sets and noise injected test sets, in order to assess how BERT pretrained representations affect model robustness.</abstract>
<identifier type="citekey">clinchant-etal-2019-use</identifier>
<identifier type="doi">10.18653/v1/D19-5611</identifier>
<location>
<url>https://aclanthology.org/D19-5611</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>108</start>
<end>117</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the use of BERT for Neural Machine Translation
%A Clinchant, Stephane
%A Jung, Kweon Woo
%A Nikoulina, Vassilina
%Y Birch, Alexandra
%Y Finch, Andrew
%Y Hayashi, Hiroaki
%Y Konstas, Ioannis
%Y Luong, Thang
%Y Neubig, Graham
%Y Oda, Yusuke
%Y Sudoh, Katsuhito
%S Proceedings of the 3rd Workshop on Neural Generation and Translation
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong
%F clinchant-etal-2019-use
%X Exploiting large pretrained models for various NMT tasks have gained a lot of visibility recently. In this work we study how BERT pretrained models could be exploited for supervised Neural Machine Translation. We compare various ways to integrate pretrained BERT model with NMT model and study the impact of the monolingual data used for BERT training on the final translation quality. We use WMT-14 English-German, IWSLT15 English-German and IWSLT14 English-Russian datasets for these experiments. In addition to standard task test set evaluation, we perform evaluation on out-of-domain test sets and noise injected test sets, in order to assess how BERT pretrained representations affect model robustness.
%R 10.18653/v1/D19-5611
%U https://aclanthology.org/D19-5611
%U https://doi.org/10.18653/v1/D19-5611
%P 108-117
Markdown (Informal)
[On the use of BERT for Neural Machine Translation](https://aclanthology.org/D19-5611) (Clinchant et al., NGT 2019)
ACL
- Stephane Clinchant, Kweon Woo Jung, and Vassilina Nikoulina. 2019. On the use of BERT for Neural Machine Translation. In Proceedings of the 3rd Workshop on Neural Generation and Translation, pages 108–117, Hong Kong. Association for Computational Linguistics.