@inproceedings{carrino-etal-2019-terminology,
title = "Terminology-Aware Segmentation and Domain Feature for the {WMT}19 Biomedical Translation Task",
author = "Carrino, Casimiro Pio and
Rafieian, Bardia and
Costa-juss{\`a}, Marta R. and
Fonollosa, Jos{\'e} A. R.",
booktitle = "Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5418",
doi = "10.18653/v1/W19-5418",
pages = "151--155",
abstract = "In this work, we give a description of the TALP-UPC systems submitted for the WMT19 Biomedical Translation Task. Our proposed strategy is NMT model-independent and relies only on one ingredient, a biomedical terminology list. We first extracted such a terminology list by labelling biomedical words in our training dataset using the BabelNet API. Then, we designed a data preparation strategy to insert the terms information at a token level. Finally, we trained the Transformer model with this terms-informed data. Our best-submitted system ranked 2nd and 3rd for Spanish-English and English-Spanish translation directions, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="carrino-etal-2019-terminology">
<titleInfo>
<title>Terminology-Aware Segmentation and Domain Feature for the WMT19 Biomedical Translation Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Casimiro</namePart>
<namePart type="given">Pio</namePart>
<namePart type="family">Carrino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bardia</namePart>
<namePart type="family">Rafieian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="given">A</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Fonollosa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-aug</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we give a description of the TALP-UPC systems submitted for the WMT19 Biomedical Translation Task. Our proposed strategy is NMT model-independent and relies only on one ingredient, a biomedical terminology list. We first extracted such a terminology list by labelling biomedical words in our training dataset using the BabelNet API. Then, we designed a data preparation strategy to insert the terms information at a token level. Finally, we trained the Transformer model with this terms-informed data. Our best-submitted system ranked 2nd and 3rd for Spanish-English and English-Spanish translation directions, respectively.</abstract>
<identifier type="citekey">carrino-etal-2019-terminology</identifier>
<identifier type="doi">10.18653/v1/W19-5418</identifier>
<location>
<url>https://aclanthology.org/W19-5418</url>
</location>
<part>
<date>2019-aug</date>
<extent unit="page">
<start>151</start>
<end>155</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Terminology-Aware Segmentation and Domain Feature for the WMT19 Biomedical Translation Task
%A Carrino, Casimiro Pio
%A Rafieian, Bardia
%A Costa-jussà, Marta R.
%A Fonollosa, José A. R.
%S Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)
%D 2019
%8 aug
%I Association for Computational Linguistics
%C Florence, Italy
%F carrino-etal-2019-terminology
%X In this work, we give a description of the TALP-UPC systems submitted for the WMT19 Biomedical Translation Task. Our proposed strategy is NMT model-independent and relies only on one ingredient, a biomedical terminology list. We first extracted such a terminology list by labelling biomedical words in our training dataset using the BabelNet API. Then, we designed a data preparation strategy to insert the terms information at a token level. Finally, we trained the Transformer model with this terms-informed data. Our best-submitted system ranked 2nd and 3rd for Spanish-English and English-Spanish translation directions, respectively.
%R 10.18653/v1/W19-5418
%U https://aclanthology.org/W19-5418
%U https://doi.org/10.18653/v1/W19-5418
%P 151-155
Markdown (Informal)
[Terminology-Aware Segmentation and Domain Feature for the WMT19 Biomedical Translation Task](https://aclanthology.org/W19-5418) (Carrino et al., 2019)
ACL