@inproceedings{etchegoyhen-etal-2016-exploiting,
title = "Exploiting a Large Strongly Comparable Corpus",
author = "Etchegoyhen, Thierry and
Azpeitia, Andoni and
P{\'e}rez, Naiara",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1560",
pages = "3523--3529",
abstract = "This article describes a large comparable corpus for Basque and Spanish and the methods employed to build a parallel resource from the original data. The EITB corpus, a strongly comparable corpus in the news domain, is to be shared with the research community, as an aid for the development and testing of methods in comparable corpora exploitation, and as basis for the improvement of data-driven machine translation systems for this language pair. Competing approaches were explored for the alignment of comparable segments in the corpus, resulting in the design of a simple method which outperformed a state-of-the-art method on the corpus test sets. The method we present is highly portable, computationally efficient, and significantly reduces deployment work, a welcome result for the exploitation of comparable corpora.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="etchegoyhen-etal-2016-exploiting">
<titleInfo>
<title>Exploiting a Large Strongly Comparable Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Etchegoyhen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andoni</namePart>
<namePart type="family">Azpeitia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naiara</namePart>
<namePart type="family">Pérez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article describes a large comparable corpus for Basque and Spanish and the methods employed to build a parallel resource from the original data. The EITB corpus, a strongly comparable corpus in the news domain, is to be shared with the research community, as an aid for the development and testing of methods in comparable corpora exploitation, and as basis for the improvement of data-driven machine translation systems for this language pair. Competing approaches were explored for the alignment of comparable segments in the corpus, resulting in the design of a simple method which outperformed a state-of-the-art method on the corpus test sets. The method we present is highly portable, computationally efficient, and significantly reduces deployment work, a welcome result for the exploitation of comparable corpora.</abstract>
<identifier type="citekey">etchegoyhen-etal-2016-exploiting</identifier>
<location>
<url>https://aclanthology.org/L16-1560</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3523</start>
<end>3529</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploiting a Large Strongly Comparable Corpus
%A Etchegoyhen, Thierry
%A Azpeitia, Andoni
%A Pérez, Naiara
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F etchegoyhen-etal-2016-exploiting
%X This article describes a large comparable corpus for Basque and Spanish and the methods employed to build a parallel resource from the original data. The EITB corpus, a strongly comparable corpus in the news domain, is to be shared with the research community, as an aid for the development and testing of methods in comparable corpora exploitation, and as basis for the improvement of data-driven machine translation systems for this language pair. Competing approaches were explored for the alignment of comparable segments in the corpus, resulting in the design of a simple method which outperformed a state-of-the-art method on the corpus test sets. The method we present is highly portable, computationally efficient, and significantly reduces deployment work, a welcome result for the exploitation of comparable corpora.
%U https://aclanthology.org/L16-1560
%P 3523-3529
Markdown (Informal)
[Exploiting a Large Strongly Comparable Corpus](https://aclanthology.org/L16-1560) (Etchegoyhen et al., LREC 2016)
ACL
- Thierry Etchegoyhen, Andoni Azpeitia, and Naiara Pérez. 2016. Exploiting a Large Strongly Comparable Corpus. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 3523–3529, Portorož, Slovenia. European Language Resources Association (ELRA).