@inproceedings{hajlaoui-etal-2014-dcep,
title = "{DCEP} -Digital Corpus of the {E}uropean Parliament",
author = {Hajlaoui, Najeh and
Kolovratnik, David and
V{\"a}yrynen, Jaakko and
Steinberger, Ralf and
Varga, Daniel},
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/943_Paper.pdf",
abstract = "We are presenting a new highly multilingual document-aligned parallel corpus called DCEP - Digital Corpus of the European Parliament. It consists of various document types covering a wide range of subject domains. With a total of 1.37 billion words in 23 languages (253 language pairs), gathered in the course of ten years, this is the largest single release of documents by a European Union institution. DCEP contains most of the content of the European Parliament{'}s official Website. It includes different document types produced between 2001 and 2012, excluding only the documents already exist in the Europarl corpus to avoid overlapping. We are presenting the typical acquisition steps of the DCEP corpus: data access, document alignment, sentence splitting, normalisation and tokenisation, and sentence alignment efforts. The sentence-level alignment is still in progress but based on some first experiments; we showed that DCEP is very useful for NLP applications, in particular for Statistical Machine Translation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hajlaoui-etal-2014-dcep">
<titleInfo>
<title>DCEP -Digital Corpus of the European Parliament</title>
</titleInfo>
<name type="personal">
<namePart type="given">Najeh</namePart>
<namePart type="family">Hajlaoui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Kolovratnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaakko</namePart>
<namePart type="family">Väyrynen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ralf</namePart>
<namePart type="family">Steinberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Varga</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>We are presenting a new highly multilingual document-aligned parallel corpus called DCEP - Digital Corpus of the European Parliament. It consists of various document types covering a wide range of subject domains. With a total of 1.37 billion words in 23 languages (253 language pairs), gathered in the course of ten years, this is the largest single release of documents by a European Union institution. DCEP contains most of the content of the European Parliament’s official Website. It includes different document types produced between 2001 and 2012, excluding only the documents already exist in the Europarl corpus to avoid overlapping. We are presenting the typical acquisition steps of the DCEP corpus: data access, document alignment, sentence splitting, normalisation and tokenisation, and sentence alignment efforts. The sentence-level alignment is still in progress but based on some first experiments; we showed that DCEP is very useful for NLP applications, in particular for Statistical Machine Translation.</abstract>
<identifier type="citekey">hajlaoui-etal-2014-dcep</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/943_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DCEP -Digital Corpus of the European Parliament
%A Hajlaoui, Najeh
%A Kolovratnik, David
%A Väyrynen, Jaakko
%A Steinberger, Ralf
%A Varga, Daniel
%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 hajlaoui-etal-2014-dcep
%X We are presenting a new highly multilingual document-aligned parallel corpus called DCEP - Digital Corpus of the European Parliament. It consists of various document types covering a wide range of subject domains. With a total of 1.37 billion words in 23 languages (253 language pairs), gathered in the course of ten years, this is the largest single release of documents by a European Union institution. DCEP contains most of the content of the European Parliament’s official Website. It includes different document types produced between 2001 and 2012, excluding only the documents already exist in the Europarl corpus to avoid overlapping. We are presenting the typical acquisition steps of the DCEP corpus: data access, document alignment, sentence splitting, normalisation and tokenisation, and sentence alignment efforts. The sentence-level alignment is still in progress but based on some first experiments; we showed that DCEP is very useful for NLP applications, in particular for Statistical Machine Translation.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/943_Paper.pdf
Markdown (Informal)
[DCEP -Digital Corpus of the European Parliament](http://www.lrec-conf.org/proceedings/lrec2014/pdf/943_Paper.pdf) (Hajlaoui et al., LREC 2014)
ACL
- Najeh Hajlaoui, David Kolovratnik, Jaakko Väyrynen, Ralf Steinberger, and Daniel Varga. 2014. DCEP -Digital Corpus of the European Parliament. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), Reykjavik, Iceland. European Language Resources Association (ELRA).