@inproceedings{duma-menzel-2018-translation,
title = "Translation of Biomedical Documents with Focus on {S}panish-{E}nglish",
author = "Duma, Mirela-Stefania and
Menzel, Wolfgang",
editor = "Bojar, Ond{\v{r}}ej and
Chatterjee, Rajen and
Federmann, Christian and
Fishel, Mark and
Graham, Yvette and
Haddow, Barry and
Huck, Matthias and
Yepes, Antonio Jimeno and
Koehn, Philipp and
Monz, Christof and
Negri, Matteo and
N{\'e}v{\'e}ol, Aur{\'e}lie and
Neves, Mariana and
Post, Matt and
Specia, Lucia and
Turchi, Marco and
Verspoor, Karin",
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>2018-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Conference on Machine Translation: Shared Task Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajen</namePart>
<namePart type="family">Chatterjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Federmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Huck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="given">Jimeno</namePart>
<namePart type="family">Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurélie</namePart>
<namePart type="family">Névéol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="family">Neves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Post</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karin</namePart>
<namePart type="family">Verspoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>2018-10</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
%Y Bojar, Ondřej
%Y Chatterjee, Rajen
%Y Federmann, Christian
%Y Fishel, Mark
%Y Graham, Yvette
%Y Haddow, Barry
%Y Huck, Matthias
%Y Yepes, Antonio Jimeno
%Y Koehn, Philipp
%Y Monz, Christof
%Y Negri, Matteo
%Y Névéol, Aurélie
%Y Neves, Mariana
%Y Post, Matt
%Y Specia, Lucia
%Y Turchi, Marco
%Y Verspoor, Karin
%S Proceedings of the Third Conference on Machine Translation: Shared Task Papers
%D 2018
%8 October
%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, WMT 2018)
ACL