@inproceedings{duma-menzel-2018-translation,
title = "Translation of Biomedical Documents with Focus on {S}panish-{E}nglish",
author = "Duma, Mirela-Stefania and
Menzel, Wolfgang",
booktitle = "Proceedings of the Third Conference on Machine Translation: Shared Task Papers",
month = oct,
year = "2018",
address = "Belgium, Brussels",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6444",
doi = "10.18653/v1/W18-6444",
pages = "637--643",
abstract = "For the WMT 2018 shared task of translating documents pertaining to the Biomedical domain, we developed a scoring formula that uses an unsophisticated and effective method of weighting term frequencies and was integrated in a data selection pipeline. The method was applied on five language pairs and it performed best on Portuguese-English, where a BLEU score of 41.84 placed it third out of seven runs submitted by three institutions. In this paper, we describe our method and results with a special focus on Spanish-English where we compare it against a state-of-the-art method. Our contribution to the task lies in introducing a fast, unsupervised method for selecting domain-specific data for training models which obtain good results using only 10{\%} of the general domain data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="duma-menzel-2018-translation">
<titleInfo>
<title>Translation of Biomedical Documents with Focus on Spanish-English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mirela-Stefania</namePart>
<namePart type="family">Duma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wolfgang</namePart>
<namePart type="family">Menzel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Conference on Machine Translation: Shared Task Papers</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Belgium, Brussels</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>For the WMT 2018 shared task of translating documents pertaining to the Biomedical domain, we developed a scoring formula that uses an unsophisticated and effective method of weighting term frequencies and was integrated in a data selection pipeline. The method was applied on five language pairs and it performed best on Portuguese-English, where a BLEU score of 41.84 placed it third out of seven runs submitted by three institutions. In this paper, we describe our method and results with a special focus on Spanish-English where we compare it against a state-of-the-art method. Our contribution to the task lies in introducing a fast, unsupervised method for selecting domain-specific data for training models which obtain good results using only 10% of the general domain data.</abstract>
<identifier type="citekey">duma-menzel-2018-translation</identifier>
<identifier type="doi">10.18653/v1/W18-6444</identifier>
<location>
<url>https://aclanthology.org/W18-6444</url>
</location>
<part>
<date>2018-oct</date>
<extent unit="page">
<start>637</start>
<end>643</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Translation of Biomedical Documents with Focus on Spanish-English
%A Duma, Mirela-Stefania
%A Menzel, Wolfgang
%S Proceedings of the Third Conference on Machine Translation: Shared Task Papers
%D 2018
%8 oct
%I Association for Computational Linguistics
%C Belgium, Brussels
%F duma-menzel-2018-translation
%X For the WMT 2018 shared task of translating documents pertaining to the Biomedical domain, we developed a scoring formula that uses an unsophisticated and effective method of weighting term frequencies and was integrated in a data selection pipeline. The method was applied on five language pairs and it performed best on Portuguese-English, where a BLEU score of 41.84 placed it third out of seven runs submitted by three institutions. In this paper, we describe our method and results with a special focus on Spanish-English where we compare it against a state-of-the-art method. Our contribution to the task lies in introducing a fast, unsupervised method for selecting domain-specific data for training models which obtain good results using only 10% of the general domain data.
%R 10.18653/v1/W18-6444
%U https://aclanthology.org/W18-6444
%U https://doi.org/10.18653/v1/W18-6444
%P 637-643
Markdown (Informal)
[Translation of Biomedical Documents with Focus on Spanish-English](https://aclanthology.org/W18-6444) (Duma & Menzel, 2018)
ACL