@inproceedings{kupietz-lungen-2014-recent,
title = "Recent Developments in {D}e{R}e{K}o",
author = {Kupietz, Marc and
L{\"u}ngen, Harald},
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/842_Paper.pdf",
pages = "2378--2385",
abstract = "This paper gives an overview of recent developments in the German Reference Corpus DeReKo in terms of growth, maximising relevant corpus strata, metadata, legal issues, and its current and future research interface. Due to the recent acquisition of new licenses, DeReKo has grown by a factor of four in the first half of 2014, mostly in the area of newspaper text, and presently contains over 24 billion word tokens. Other strata, like fictional texts, web corpora, in particular CMC texts, and spoken but conceptually written texts have also increased significantly. We report on the newly acquired corpora that led to the major increase, on the principles and strategies behind our corpus acquisition activities, and on our solutions for the emerging legal, organisational, and technical challenges.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kupietz-lungen-2014-recent">
<titleInfo>
<title>Recent Developments in DeReKo</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">Harald</namePart>
<namePart type="family">Lüngen</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>This paper gives an overview of recent developments in the German Reference Corpus DeReKo in terms of growth, maximising relevant corpus strata, metadata, legal issues, and its current and future research interface. Due to the recent acquisition of new licenses, DeReKo has grown by a factor of four in the first half of 2014, mostly in the area of newspaper text, and presently contains over 24 billion word tokens. Other strata, like fictional texts, web corpora, in particular CMC texts, and spoken but conceptually written texts have also increased significantly. We report on the newly acquired corpora that led to the major increase, on the principles and strategies behind our corpus acquisition activities, and on our solutions for the emerging legal, organisational, and technical challenges.</abstract>
<identifier type="citekey">kupietz-lungen-2014-recent</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/842_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2378</start>
<end>2385</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Recent Developments in DeReKo
%A Kupietz, Marc
%A Lüngen, Harald
%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 kupietz-lungen-2014-recent
%X This paper gives an overview of recent developments in the German Reference Corpus DeReKo in terms of growth, maximising relevant corpus strata, metadata, legal issues, and its current and future research interface. Due to the recent acquisition of new licenses, DeReKo has grown by a factor of four in the first half of 2014, mostly in the area of newspaper text, and presently contains over 24 billion word tokens. Other strata, like fictional texts, web corpora, in particular CMC texts, and spoken but conceptually written texts have also increased significantly. We report on the newly acquired corpora that led to the major increase, on the principles and strategies behind our corpus acquisition activities, and on our solutions for the emerging legal, organisational, and technical challenges.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/842_Paper.pdf
%P 2378-2385
Markdown (Informal)
[Recent Developments in DeReKo](http://www.lrec-conf.org/proceedings/lrec2014/pdf/842_Paper.pdf) (Kupietz & Lüngen, LREC 2014)
ACL
- Marc Kupietz and Harald Lüngen. 2014. Recent Developments in DeReKo. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2378–2385, Reykjavik, Iceland. European Language Resources Association (ELRA).