@inproceedings{kupietz-etal-2010-german,
title = "The {G}erman Reference Corpus {D}e{R}e{K}o: A Primordial Sample for Linguistic Research",
author = "Kupietz, Marc and
Belica, Cyril and
Keibel, Holger and
Witt, Andreas",
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/414_Paper.pdf",
abstract = {This paper describes DeReKo (Deutsches Referenzkorpus), the Archive of General Reference Corpora of Contemporary Written German at the Institut f{\"u}r Deutsche Sprache (IDS) in Mannheim, and the rationale behind its development. We discuss its design, its legal background, how to access it, available metadata, linguistic annotation layers, underlying standards, ongoing developments, and aspects of using the archive for empirical linguistic research. The focus of the paper is on the advantages of DeReKo's design as a primordial sample from which virtual corpora can be drawn for the specific purposes of individual studies. Both concepts, primordial sample and virtual corpus are explained and illustrated in detail. Furthermore, we describe in more detail how DeReKo deals with the fact that all its texts are subject to third parties' intellectual property rights, and how it deals with the issue of replicability, which is particularly challenging given DeReKo's dynamic growth and the possibility to construct from it an open number of virtual corpora.},
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kupietz-etal-2010-german">
<titleInfo>
<title>The German Reference Corpus DeReKo: A Primordial Sample for Linguistic Research</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Kupietz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cyril</namePart>
<namePart type="family">Belica</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Holger</namePart>
<namePart type="family">Keibel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Witt</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>This paper describes DeReKo (Deutsches Referenzkorpus), the Archive of General Reference Corpora of Contemporary Written German at the Institut für Deutsche Sprache (IDS) in Mannheim, and the rationale behind its development. We discuss its design, its legal background, how to access it, available metadata, linguistic annotation layers, underlying standards, ongoing developments, and aspects of using the archive for empirical linguistic research. The focus of the paper is on the advantages of DeReKo’s design as a primordial sample from which virtual corpora can be drawn for the specific purposes of individual studies. Both concepts, primordial sample and virtual corpus are explained and illustrated in detail. Furthermore, we describe in more detail how DeReKo deals with the fact that all its texts are subject to third parties’ intellectual property rights, and how it deals with the issue of replicability, which is particularly challenging given DeReKo’s dynamic growth and the possibility to construct from it an open number of virtual corpora.</abstract>
<identifier type="citekey">kupietz-etal-2010-german</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/414_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The German Reference Corpus DeReKo: A Primordial Sample for Linguistic Research
%A Kupietz, Marc
%A Belica, Cyril
%A Keibel, Holger
%A Witt, Andreas
%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 kupietz-etal-2010-german
%X This paper describes DeReKo (Deutsches Referenzkorpus), the Archive of General Reference Corpora of Contemporary Written German at the Institut für Deutsche Sprache (IDS) in Mannheim, and the rationale behind its development. We discuss its design, its legal background, how to access it, available metadata, linguistic annotation layers, underlying standards, ongoing developments, and aspects of using the archive for empirical linguistic research. The focus of the paper is on the advantages of DeReKo’s design as a primordial sample from which virtual corpora can be drawn for the specific purposes of individual studies. Both concepts, primordial sample and virtual corpus are explained and illustrated in detail. Furthermore, we describe in more detail how DeReKo deals with the fact that all its texts are subject to third parties’ intellectual property rights, and how it deals with the issue of replicability, which is particularly challenging given DeReKo’s dynamic growth and the possibility to construct from it an open number of virtual corpora.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/414_Paper.pdf
Markdown (Informal)
[The German Reference Corpus DeReKo: A Primordial Sample for Linguistic Research](http://www.lrec-conf.org/proceedings/lrec2010/pdf/414_Paper.pdf) (Kupietz et al., LREC 2010)
ACL