@inproceedings{san-vicente-manterola-2012-paco2,
title = "{P}a{C}o2: A Fully Automated tool for gathering Parallel Corpora from the Web",
author = "San Vicente, I{\~n}aki and
Manterola, Iker",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/231_Paper.pdf",
pages = "1--6",
abstract = "The importance of parallel corpora in the NLP field is fully acknowledged. This paper presents a tool that can build parallel corpora given just a seed word list and a pair of languages. Our approach is similar to others proposed in the literature, but introduces a new phase to the process. While most of the systems leave the task of finding websites containing parallel content up to the user, PaCo2 (Parallel Corpora Collector) takes care of that as well. The tool is language independent as far as possible, and adapting the system to work with new languages is fairly straightforward. Evaluation of the different modules has been carried out for Basque-Spanish, Spanish-English and Portuguese-English language pairs. Even though there is still room for improvement, results are positive. Results show that the corpora created have very good quality translations units, and the quality is maintained for the various language pairs. Details of the corpora created up until now are also provided.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="san-vicente-manterola-2012-paco2">
<titleInfo>
<title>PaCo2: A Fully Automated tool for gathering Parallel Corpora from the Web</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iñaki</namePart>
<namePart type="family">San Vicente</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iker</namePart>
<namePart type="family">Manterola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The importance of parallel corpora in the NLP field is fully acknowledged. This paper presents a tool that can build parallel corpora given just a seed word list and a pair of languages. Our approach is similar to others proposed in the literature, but introduces a new phase to the process. While most of the systems leave the task of finding websites containing parallel content up to the user, PaCo2 (Parallel Corpora Collector) takes care of that as well. The tool is language independent as far as possible, and adapting the system to work with new languages is fairly straightforward. Evaluation of the different modules has been carried out for Basque-Spanish, Spanish-English and Portuguese-English language pairs. Even though there is still room for improvement, results are positive. Results show that the corpora created have very good quality translations units, and the quality is maintained for the various language pairs. Details of the corpora created up until now are also provided.</abstract>
<identifier type="citekey">san-vicente-manterola-2012-paco2</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/231_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>1</start>
<end>6</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PaCo2: A Fully Automated tool for gathering Parallel Corpora from the Web
%A San Vicente, Iñaki
%A Manterola, Iker
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F san-vicente-manterola-2012-paco2
%X The importance of parallel corpora in the NLP field is fully acknowledged. This paper presents a tool that can build parallel corpora given just a seed word list and a pair of languages. Our approach is similar to others proposed in the literature, but introduces a new phase to the process. While most of the systems leave the task of finding websites containing parallel content up to the user, PaCo2 (Parallel Corpora Collector) takes care of that as well. The tool is language independent as far as possible, and adapting the system to work with new languages is fairly straightforward. Evaluation of the different modules has been carried out for Basque-Spanish, Spanish-English and Portuguese-English language pairs. Even though there is still room for improvement, results are positive. Results show that the corpora created have very good quality translations units, and the quality is maintained for the various language pairs. Details of the corpora created up until now are also provided.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/231_Paper.pdf
%P 1-6
Markdown (Informal)
[PaCo2: A Fully Automated tool for gathering Parallel Corpora from the Web](http://www.lrec-conf.org/proceedings/lrec2012/pdf/231_Paper.pdf) (San Vicente & Manterola, LREC 2012)
ACL