@inproceedings{kestemont-etal-2012-netlog,
title = "The Netlog Corpus. A Resource for the Study of {F}lemish {D}utch {I}nternet Language",
author = "Kestemont, Mike and
Peersman, Claudia and
De Decker, Benny and
De Pauw, Guy and
Luyckx, Kim and
Morante, Roser and
Vaassen, Frederik and
van de Loo, Janneke and
Daelemans, Walter",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/938_Paper.pdf",
pages = "1569--1572",
abstract = "Although in recent years numerous forms of Internet communication ― such as e-mail, blogs, chat rooms and social network environments ― have emerged, balanced corpora of Internet speech with trustworthy meta-information (e.g. age and gender) or linguistic annotations are still limited. In this paper we present a large corpus of Flemish Dutch chat posts that were collected from the Belgian online social network Netlog. For all of these posts we also acquired the users' profile information, making this corpus a unique resource for computational and sociolinguistic research. However, for analyzing such a corpus on a large scale, NLP tools are required for e.g. automatic POS tagging or lemmatization. Because many NLP tools fail to correctly analyze the surface forms of chat language usage, we propose to normalize this anomalous' input into a format suitable for existing NLP solutions for standard Dutch. Additionally, we have annotated a substantial part of the corpus (i.e. the Chatty subset) to provide a gold standard for the evaluation of future approaches to automatic (Flemish) chat language normalization.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kestemont-etal-2012-netlog">
<titleInfo>
<title>The Netlog Corpus. A Resource for the Study of Flemish Dutch Internet Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Kestemont</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Peersman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benny</namePart>
<namePart type="family">De Decker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">De Pauw</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kim</namePart>
<namePart type="family">Luyckx</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roser</namePart>
<namePart type="family">Morante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederik</namePart>
<namePart type="family">Vaassen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Janneke</namePart>
<namePart type="family">van de Loo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walter</namePart>
<namePart type="family">Daelemans</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Although in recent years numerous forms of Internet communication ― such as e-mail, blogs, chat rooms and social network environments ― have emerged, balanced corpora of Internet speech with trustworthy meta-information (e.g. age and gender) or linguistic annotations are still limited. In this paper we present a large corpus of Flemish Dutch chat posts that were collected from the Belgian online social network Netlog. For all of these posts we also acquired the users’ profile information, making this corpus a unique resource for computational and sociolinguistic research. However, for analyzing such a corpus on a large scale, NLP tools are required for e.g. automatic POS tagging or lemmatization. Because many NLP tools fail to correctly analyze the surface forms of chat language usage, we propose to normalize this anomalous’ input into a format suitable for existing NLP solutions for standard Dutch. Additionally, we have annotated a substantial part of the corpus (i.e. the Chatty subset) to provide a gold standard for the evaluation of future approaches to automatic (Flemish) chat language normalization.</abstract>
<identifier type="citekey">kestemont-etal-2012-netlog</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/938_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>1569</start>
<end>1572</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Netlog Corpus. A Resource for the Study of Flemish Dutch Internet Language
%A Kestemont, Mike
%A Peersman, Claudia
%A De Decker, Benny
%A De Pauw, Guy
%A Luyckx, Kim
%A Morante, Roser
%A Vaassen, Frederik
%A van de Loo, Janneke
%A Daelemans, Walter
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F kestemont-etal-2012-netlog
%X Although in recent years numerous forms of Internet communication ― such as e-mail, blogs, chat rooms and social network environments ― have emerged, balanced corpora of Internet speech with trustworthy meta-information (e.g. age and gender) or linguistic annotations are still limited. In this paper we present a large corpus of Flemish Dutch chat posts that were collected from the Belgian online social network Netlog. For all of these posts we also acquired the users’ profile information, making this corpus a unique resource for computational and sociolinguistic research. However, for analyzing such a corpus on a large scale, NLP tools are required for e.g. automatic POS tagging or lemmatization. Because many NLP tools fail to correctly analyze the surface forms of chat language usage, we propose to normalize this anomalous’ input into a format suitable for existing NLP solutions for standard Dutch. Additionally, we have annotated a substantial part of the corpus (i.e. the Chatty subset) to provide a gold standard for the evaluation of future approaches to automatic (Flemish) chat language normalization.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/938_Paper.pdf
%P 1569-1572
Markdown (Informal)
[The Netlog Corpus. A Resource for the Study of Flemish Dutch Internet Language](http://www.lrec-conf.org/proceedings/lrec2012/pdf/938_Paper.pdf) (Kestemont et al., LREC 2012)
ACL
- Mike Kestemont, Claudia Peersman, Benny De Decker, Guy De Pauw, Kim Luyckx, Roser Morante, Frederik Vaassen, Janneke van de Loo, and Walter Daelemans. 2012. The Netlog Corpus. A Resource for the Study of Flemish Dutch Internet Language. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 1569–1572, Istanbul, Turkey. European Language Resources Association (ELRA).