@inproceedings{rafieian-costa-jussa-2021-high,
title = "High Frequent In-domain Words Segmentation and Forward Translation for the {WMT}21 Biomedical Task",
author = "Rafieian, Bardia and
Costa-jussa, Marta R.",
booktitle = "Proceedings of the Sixth Conference on Machine Translation",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wmt-1.87",
pages = "863--867",
abstract = "This paper reports the optimization of using the out-of-domain data in the Biomedical translation task. We firstly optimized our parallel training dataset using the BabelNet in-domain terminology words. Afterward, to increase the training set, we studied the effects of the out-of-domain data on biomedical translation tasks, and we created a mixture of in-domain and out-of-domain training sets and added more in-domain data using forward translation in the English-Spanish task. Finally, with a simple bpe optimization method, we increased the number of in-domain sub-words in our mixed training set and trained the Transformer model on the generated data. Results show improvements using our proposed method.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rafieian-costa-jussa-2021-high">
<titleInfo>
<title>High Frequent In-domain Words Segmentation and Forward Translation for the WMT21 Biomedical Task</title>
</titleInfo>
<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-jussa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth 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 reports the optimization of using the out-of-domain data in the Biomedical translation task. We firstly optimized our parallel training dataset using the BabelNet in-domain terminology words. Afterward, to increase the training set, we studied the effects of the out-of-domain data on biomedical translation tasks, and we created a mixture of in-domain and out-of-domain training sets and added more in-domain data using forward translation in the English-Spanish task. Finally, with a simple bpe optimization method, we increased the number of in-domain sub-words in our mixed training set and trained the Transformer model on the generated data. Results show improvements using our proposed method.</abstract>
<identifier type="citekey">rafieian-costa-jussa-2021-high</identifier>
<location>
<url>https://aclanthology.org/2021.wmt-1.87</url>
</location>
<part>
<date>2021-nov</date>
<extent unit="page">
<start>863</start>
<end>867</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T High Frequent In-domain Words Segmentation and Forward Translation for the WMT21 Biomedical Task
%A Rafieian, Bardia
%A Costa-jussa, Marta R.
%S Proceedings of the Sixth Conference on Machine Translation
%D 2021
%8 nov
%I Association for Computational Linguistics
%C Online
%F rafieian-costa-jussa-2021-high
%X This paper reports the optimization of using the out-of-domain data in the Biomedical translation task. We firstly optimized our parallel training dataset using the BabelNet in-domain terminology words. Afterward, to increase the training set, we studied the effects of the out-of-domain data on biomedical translation tasks, and we created a mixture of in-domain and out-of-domain training sets and added more in-domain data using forward translation in the English-Spanish task. Finally, with a simple bpe optimization method, we increased the number of in-domain sub-words in our mixed training set and trained the Transformer model on the generated data. Results show improvements using our proposed method.
%U https://aclanthology.org/2021.wmt-1.87
%P 863-867
Markdown (Informal)
[High Frequent In-domain Words Segmentation and Forward Translation for the WMT21 Biomedical Task](https://aclanthology.org/2021.wmt-1.87) (Rafieian & Costa-jussa, WMT 2021)
ACL