@inproceedings{corral-saralegi-2020-elhuyar,
title = "Elhuyar submission to the Biomedical Translation Task 2020 on terminology and abstracts translation",
author = "Corral, Ander and
Saralegi, Xabier",
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-1.87",
pages = "813--819",
abstract = "This article describes the systems submitted by Elhuyar to the 2020 Biomedical Translation Shared Task, specifically the systems presented in the subtasks of terminology translation for English-Basque and abstract translation for English-Basque and English-Spanish. In all cases a Transformer architecture was chosen and we studied different strategies to combine open domain data with biomedical domain data for building the training corpora. For the English-Basque pair, given the scarcity of parallel corpora in the biomedical domain, we set out to create domain training data in a synthetic way. The systems presented in the terminology and abstract translation subtasks for the English-Basque language pair ranked first in their respective tasks among four participants, achieving 0.78 accuracy for terminology translation and a BLEU of 0.1279 for the translation of abstracts. In the abstract translation task for the English-Spanish pair our team ranked second (BLEU=0.4498) in the case of OK sentences.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="corral-saralegi-2020-elhuyar">
<titleInfo>
<title>Elhuyar submission to the Biomedical Translation Task 2020 on terminology and abstracts translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ander</namePart>
<namePart type="family">Corral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xabier</namePart>
<namePart type="family">Saralegi</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 article describes the systems submitted by Elhuyar to the 2020 Biomedical Translation Shared Task, specifically the systems presented in the subtasks of terminology translation for English-Basque and abstract translation for English-Basque and English-Spanish. In all cases a Transformer architecture was chosen and we studied different strategies to combine open domain data with biomedical domain data for building the training corpora. For the English-Basque pair, given the scarcity of parallel corpora in the biomedical domain, we set out to create domain training data in a synthetic way. The systems presented in the terminology and abstract translation subtasks for the English-Basque language pair ranked first in their respective tasks among four participants, achieving 0.78 accuracy for terminology translation and a BLEU of 0.1279 for the translation of abstracts. In the abstract translation task for the English-Spanish pair our team ranked second (BLEU=0.4498) in the case of OK sentences.</abstract>
<identifier type="citekey">corral-saralegi-2020-elhuyar</identifier>
<location>
<url>https://aclanthology.org/2020.wmt-1.87</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>813</start>
<end>819</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Elhuyar submission to the Biomedical Translation Task 2020 on terminology and abstracts translation
%A Corral, Ander
%A Saralegi, Xabier
%S Proceedings of the Fifth Conference on Machine Translation
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F corral-saralegi-2020-elhuyar
%X This article describes the systems submitted by Elhuyar to the 2020 Biomedical Translation Shared Task, specifically the systems presented in the subtasks of terminology translation for English-Basque and abstract translation for English-Basque and English-Spanish. In all cases a Transformer architecture was chosen and we studied different strategies to combine open domain data with biomedical domain data for building the training corpora. For the English-Basque pair, given the scarcity of parallel corpora in the biomedical domain, we set out to create domain training data in a synthetic way. The systems presented in the terminology and abstract translation subtasks for the English-Basque language pair ranked first in their respective tasks among four participants, achieving 0.78 accuracy for terminology translation and a BLEU of 0.1279 for the translation of abstracts. In the abstract translation task for the English-Spanish pair our team ranked second (BLEU=0.4498) in the case of OK sentences.
%U https://aclanthology.org/2020.wmt-1.87
%P 813-819
Markdown (Informal)
[Elhuyar submission to the Biomedical Translation Task 2020 on terminology and abstracts translation](https://aclanthology.org/2020.wmt-1.87) (Corral & Saralegi, WMT 2020)
ACL