@inproceedings{de-clercq-perez-2010-data,
title = "Data Collection and {IPR} in Multilingual Parallel Corpora. {D}utch Parallel Corpus",
author = "De Clercq, Orph{\'e}e and
Perez, Maribel Montero",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/204_Paper.pdf",
abstract = "After three years of work the Dutch Parallel Corpus (DPC) project has reached an end. The finalized corpus is a ten-million-word high-quality sentence-aligned bidirectional parallel corpus of Dutch, English and French, with Dutch as central language. In this paper we present the corpus and try to formulate some basic data collection principles, based on the work that was carried out for the project. Building a corpus is a difficult and time-consuming task, especially when every text sample included has to be cleared from copyrights. The DPC is balanced according to five text types (literature, journalistic texts, instructive texts, administrative texts and texts treating external communication) and four translation directions (Dutch-English, English-Dutch, Dutch-French and French-Dutch). All the text material was cleared from copyrights. The data collection process necessitated the involvement of different text providers, which resulted in drawing up four different licence agreements. Problems such as an unknown source language, copyright issues and changes to the corpus design are discussed in close detail and illustrated with examples so as to be of help to future corpus compilers.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-clercq-perez-2010-data">
<titleInfo>
<title>Data Collection and IPR in Multilingual Parallel Corpora. Dutch Parallel Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Orphée</namePart>
<namePart type="family">De Clercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maribel</namePart>
<namePart type="given">Montero</namePart>
<namePart type="family">Perez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>After three years of work the Dutch Parallel Corpus (DPC) project has reached an end. The finalized corpus is a ten-million-word high-quality sentence-aligned bidirectional parallel corpus of Dutch, English and French, with Dutch as central language. In this paper we present the corpus and try to formulate some basic data collection principles, based on the work that was carried out for the project. Building a corpus is a difficult and time-consuming task, especially when every text sample included has to be cleared from copyrights. The DPC is balanced according to five text types (literature, journalistic texts, instructive texts, administrative texts and texts treating external communication) and four translation directions (Dutch-English, English-Dutch, Dutch-French and French-Dutch). All the text material was cleared from copyrights. The data collection process necessitated the involvement of different text providers, which resulted in drawing up four different licence agreements. Problems such as an unknown source language, copyright issues and changes to the corpus design are discussed in close detail and illustrated with examples so as to be of help to future corpus compilers.</abstract>
<identifier type="citekey">de-clercq-perez-2010-data</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/204_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Collection and IPR in Multilingual Parallel Corpora. Dutch Parallel Corpus
%A De Clercq, Orphée
%A Perez, Maribel Montero
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F de-clercq-perez-2010-data
%X After three years of work the Dutch Parallel Corpus (DPC) project has reached an end. The finalized corpus is a ten-million-word high-quality sentence-aligned bidirectional parallel corpus of Dutch, English and French, with Dutch as central language. In this paper we present the corpus and try to formulate some basic data collection principles, based on the work that was carried out for the project. Building a corpus is a difficult and time-consuming task, especially when every text sample included has to be cleared from copyrights. The DPC is balanced according to five text types (literature, journalistic texts, instructive texts, administrative texts and texts treating external communication) and four translation directions (Dutch-English, English-Dutch, Dutch-French and French-Dutch). All the text material was cleared from copyrights. The data collection process necessitated the involvement of different text providers, which resulted in drawing up four different licence agreements. Problems such as an unknown source language, copyright issues and changes to the corpus design are discussed in close detail and illustrated with examples so as to be of help to future corpus compilers.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/204_Paper.pdf
Markdown (Informal)
[Data Collection and IPR in Multilingual Parallel Corpora. Dutch Parallel Corpus](http://www.lrec-conf.org/proceedings/lrec2010/pdf/204_Paper.pdf) (De Clercq & Perez, LREC 2010)
ACL