@inproceedings{skadins-etal-2014-billions,
title = "Billions of Parallel Words for Free: Building and Using the {EU} Bookshop Corpus",
author = {Skadi{\c{n}}{\v{s}}, Raivis and
Tiedemann, J{\"o}rg and
Rozis, Roberts and
Deksne, Daiga},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/846_Paper.pdf",
pages = "1850--1855",
abstract = "The European Union is a great source of high quality documents with translations into several languages. Parallel corpora from its publications are frequently used in various tasks, machine translation in particular. A source that has not systematically been explored yet is the EU Bookshop ― an online service and archive of publications from various European institutions. The service contains a large body of publications in the 24 official of the EU. This paper describes our efforts in collecting those publications and converting them to a format that is useful for natural language processing in particular statistical machine translation. We report our procedure of crawling the website and various pre-processing steps that were necessary to clean up the data after the conversion from the original PDF files. Furthermore, we demonstrate the use of this dataset in training SMT models for English, French, German, Spanish, and Latvian.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="skadins-etal-2014-billions">
<titleInfo>
<title>Billions of Parallel Words for Free: Building and Using the EU Bookshop Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raivis</namePart>
<namePart type="family">Skadiņš</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberts</namePart>
<namePart type="family">Rozis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daiga</namePart>
<namePart type="family">Deksne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The European Union is a great source of high quality documents with translations into several languages. Parallel corpora from its publications are frequently used in various tasks, machine translation in particular. A source that has not systematically been explored yet is the EU Bookshop ― an online service and archive of publications from various European institutions. The service contains a large body of publications in the 24 official of the EU. This paper describes our efforts in collecting those publications and converting them to a format that is useful for natural language processing in particular statistical machine translation. We report our procedure of crawling the website and various pre-processing steps that were necessary to clean up the data after the conversion from the original PDF files. Furthermore, we demonstrate the use of this dataset in training SMT models for English, French, German, Spanish, and Latvian.</abstract>
<identifier type="citekey">skadins-etal-2014-billions</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/846_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1850</start>
<end>1855</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Billions of Parallel Words for Free: Building and Using the EU Bookshop Corpus
%A Skadiņš, Raivis
%A Tiedemann, Jörg
%A Rozis, Roberts
%A Deksne, Daiga
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F skadins-etal-2014-billions
%X The European Union is a great source of high quality documents with translations into several languages. Parallel corpora from its publications are frequently used in various tasks, machine translation in particular. A source that has not systematically been explored yet is the EU Bookshop ― an online service and archive of publications from various European institutions. The service contains a large body of publications in the 24 official of the EU. This paper describes our efforts in collecting those publications and converting them to a format that is useful for natural language processing in particular statistical machine translation. We report our procedure of crawling the website and various pre-processing steps that were necessary to clean up the data after the conversion from the original PDF files. Furthermore, we demonstrate the use of this dataset in training SMT models for English, French, German, Spanish, and Latvian.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/846_Paper.pdf
%P 1850-1855
Markdown (Informal)
[Billions of Parallel Words for Free: Building and Using the EU Bookshop Corpus](http://www.lrec-conf.org/proceedings/lrec2014/pdf/846_Paper.pdf) (Skadiņš et al., LREC 2014)
ACL