@inproceedings{jauregi-unanue-piccardi-2020-pretrained,
title = "Pretrained Language Models and Backtranslation for {E}nglish-{B}asque Biomedical Neural Machine Translation",
author = "Jauregi Unanue, Inigo and
Piccardi, Massimo",
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.89",
pages = "826--832",
abstract = "This paper describes the machine translation systems proposed by the University of Technology Sydney Natural Language Processing (UTS{\_}NLP) team for the WMT20 English-Basque biomedical translation tasks. Due to the limited parallel corpora available, we have proposed to train a BERT-fused NMT model that leverages the use of pretrained language models. Furthermore, we have augmented the training corpus by backtranslating monolingual data. Our experiments show that NMT models in low-resource scenarios can benefit from combining these two training techniques, with improvements of up to 6.16 BLEU percentual points in the case of biomedical abstract translations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jauregi-unanue-piccardi-2020-pretrained">
<titleInfo>
<title>Pretrained Language Models and Backtranslation for English-Basque Biomedical Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Inigo</namePart>
<namePart type="family">Jauregi Unanue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Massimo</namePart>
<namePart type="family">Piccardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Conference on Machine Translation</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the machine translation systems proposed by the University of Technology Sydney Natural Language Processing (UTS_NLP) team for the WMT20 English-Basque biomedical translation tasks. Due to the limited parallel corpora available, we have proposed to train a BERT-fused NMT model that leverages the use of pretrained language models. Furthermore, we have augmented the training corpus by backtranslating monolingual data. Our experiments show that NMT models in low-resource scenarios can benefit from combining these two training techniques, with improvements of up to 6.16 BLEU percentual points in the case of biomedical abstract translations.</abstract>
<identifier type="citekey">jauregi-unanue-piccardi-2020-pretrained</identifier>
<location>
<url>https://aclanthology.org/2020.wmt-1.89</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>826</start>
<end>832</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pretrained Language Models and Backtranslation for English-Basque Biomedical Neural Machine Translation
%A Jauregi Unanue, Inigo
%A Piccardi, Massimo
%S Proceedings of the Fifth Conference on Machine Translation
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F jauregi-unanue-piccardi-2020-pretrained
%X This paper describes the machine translation systems proposed by the University of Technology Sydney Natural Language Processing (UTS_NLP) team for the WMT20 English-Basque biomedical translation tasks. Due to the limited parallel corpora available, we have proposed to train a BERT-fused NMT model that leverages the use of pretrained language models. Furthermore, we have augmented the training corpus by backtranslating monolingual data. Our experiments show that NMT models in low-resource scenarios can benefit from combining these two training techniques, with improvements of up to 6.16 BLEU percentual points in the case of biomedical abstract translations.
%U https://aclanthology.org/2020.wmt-1.89
%P 826-832
Markdown (Informal)
[Pretrained Language Models and Backtranslation for English-Basque Biomedical Neural Machine Translation](https://aclanthology.org/2020.wmt-1.89) (Jauregi Unanue & Piccardi, WMT 2020)
ACL