@inproceedings{reynaert-etal-2010-balancing,
title = "Balancing {S}o{N}a{R}: {IPR} versus Processing Issues in a 500-Million-Word Written {D}utch Reference Corpus",
author = "Reynaert, Martin and
Oostdijk, Nelleke and
De Clercq, Orph{\'e}e and
van den Heuvel, Henk and
de Jong, Franciska",
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 = "https://aclanthology.org/L10-1376/",
abstract = "In The Low Countries, a major reference corpus for written Dutch is being built. We discuss the interplay between data acquisition and data processing during the creation of the SoNaR Corpus. Based on developments in traditional corpus compiling and new web harvesting approaches, SoNaR is designed to contain 500 million words, balanced over 36 text types including both traditional and new media texts. Beside its balanced design, every text sample included in SoNaR will have its IPR issues settled to the largest extent possible. This data collection task presents many challenges because every decision taken on the level of text acquisition has ramifications for the level of processing and the general usability of the corpus. As far as the traditional text types are concerned, each text brings its own processing requirements and issues. For new media texts - SMS, chat - the problem is even more complex, issues such as anonimity, recognizability and citation right, all present problems that have to be tackled. The solutions actually lead to the creation of two corpora: a gigaword SoNaR, IPR-cleared for research purposes, and the smaller - of commissioned size - more privacy compliant SoNaR, IPR-cleared for commercial purposes as well."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reynaert-etal-2010-balancing">
<titleInfo>
<title>Balancing SoNaR: IPR versus Processing Issues in a 500-Million-Word Written Dutch Reference Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Reynaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nelleke</namePart>
<namePart type="family">Oostdijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Franciska</namePart>
<namePart type="family">de Jong</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>In The Low Countries, a major reference corpus for written Dutch is being built. We discuss the interplay between data acquisition and data processing during the creation of the SoNaR Corpus. Based on developments in traditional corpus compiling and new web harvesting approaches, SoNaR is designed to contain 500 million words, balanced over 36 text types including both traditional and new media texts. Beside its balanced design, every text sample included in SoNaR will have its IPR issues settled to the largest extent possible. This data collection task presents many challenges because every decision taken on the level of text acquisition has ramifications for the level of processing and the general usability of the corpus. As far as the traditional text types are concerned, each text brings its own processing requirements and issues. For new media texts - SMS, chat - the problem is even more complex, issues such as anonimity, recognizability and citation right, all present problems that have to be tackled. The solutions actually lead to the creation of two corpora: a gigaword SoNaR, IPR-cleared for research purposes, and the smaller - of commissioned size - more privacy compliant SoNaR, IPR-cleared for commercial purposes as well.</abstract>
<identifier type="citekey">reynaert-etal-2010-balancing</identifier>
<location>
<url>https://aclanthology.org/L10-1376/</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Balancing SoNaR: IPR versus Processing Issues in a 500-Million-Word Written Dutch Reference Corpus
%A Reynaert, Martin
%A Oostdijk, Nelleke
%A De Clercq, Orphée
%A van den Heuvel, Henk
%A de Jong, Franciska
%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 reynaert-etal-2010-balancing
%X In The Low Countries, a major reference corpus for written Dutch is being built. We discuss the interplay between data acquisition and data processing during the creation of the SoNaR Corpus. Based on developments in traditional corpus compiling and new web harvesting approaches, SoNaR is designed to contain 500 million words, balanced over 36 text types including both traditional and new media texts. Beside its balanced design, every text sample included in SoNaR will have its IPR issues settled to the largest extent possible. This data collection task presents many challenges because every decision taken on the level of text acquisition has ramifications for the level of processing and the general usability of the corpus. As far as the traditional text types are concerned, each text brings its own processing requirements and issues. For new media texts - SMS, chat - the problem is even more complex, issues such as anonimity, recognizability and citation right, all present problems that have to be tackled. The solutions actually lead to the creation of two corpora: a gigaword SoNaR, IPR-cleared for research purposes, and the smaller - of commissioned size - more privacy compliant SoNaR, IPR-cleared for commercial purposes as well.
%U https://aclanthology.org/L10-1376/
Markdown (Informal)
[Balancing SoNaR: IPR versus Processing Issues in a 500-Million-Word Written Dutch Reference Corpus](https://aclanthology.org/L10-1376/) (Reynaert et al., LREC 2010)
ACL