@inproceedings{rehbein-etal-2014-kiezdeutsch,
title = "The {K}iez{D}eutsch Korpus ({K}i{DK}o) Release 1.0",
author = {Rehbein, Ines and
Schalowski, S{\"o}ren and
Wiese, Heike},
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/1081_Paper.pdf",
pages = "3927--3934",
abstract = "This paper presents the first release of the KiezDeutsch Korpus (KiDKo), a new language resource with multiparty spoken dialogues of Kiezdeutsch, a newly emerging language variety spoken by adolescents from multiethnic urban areas in Germany. The first release of the corpus includes the transcriptions of the data as well as a normalisation layer and part-of-speech annotations. In the paper, we describe the main features of the new resource and then focus on automatic POS tagging of informal spoken language. Our tagger achieves an accuracy of nearly 97{\%} on KiDKo. While we did not succeed in further improving the tagger using ensemble tagging, we present our approach to using the tagger ensembles for identifying error patterns in the automatically tagged data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rehbein-etal-2014-kiezdeutsch">
<titleInfo>
<title>The KiezDeutsch Korpus (KiDKo) Release 1.0</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ines</namePart>
<namePart type="family">Rehbein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sören</namePart>
<namePart type="family">Schalowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heike</namePart>
<namePart type="family">Wiese</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 presents the first release of the KiezDeutsch Korpus (KiDKo), a new language resource with multiparty spoken dialogues of Kiezdeutsch, a newly emerging language variety spoken by adolescents from multiethnic urban areas in Germany. The first release of the corpus includes the transcriptions of the data as well as a normalisation layer and part-of-speech annotations. In the paper, we describe the main features of the new resource and then focus on automatic POS tagging of informal spoken language. Our tagger achieves an accuracy of nearly 97% on KiDKo. While we did not succeed in further improving the tagger using ensemble tagging, we present our approach to using the tagger ensembles for identifying error patterns in the automatically tagged data.</abstract>
<identifier type="citekey">rehbein-etal-2014-kiezdeutsch</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1081_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3927</start>
<end>3934</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The KiezDeutsch Korpus (KiDKo) Release 1.0
%A Rehbein, Ines
%A Schalowski, Sören
%A Wiese, Heike
%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 rehbein-etal-2014-kiezdeutsch
%X This paper presents the first release of the KiezDeutsch Korpus (KiDKo), a new language resource with multiparty spoken dialogues of Kiezdeutsch, a newly emerging language variety spoken by adolescents from multiethnic urban areas in Germany. The first release of the corpus includes the transcriptions of the data as well as a normalisation layer and part-of-speech annotations. In the paper, we describe the main features of the new resource and then focus on automatic POS tagging of informal spoken language. Our tagger achieves an accuracy of nearly 97% on KiDKo. While we did not succeed in further improving the tagger using ensemble tagging, we present our approach to using the tagger ensembles for identifying error patterns in the automatically tagged data.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1081_Paper.pdf
%P 3927-3934
Markdown (Informal)
[The KiezDeutsch Korpus (KiDKo) Release 1.0](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1081_Paper.pdf) (Rehbein et al., LREC 2014)
ACL
- Ines Rehbein, Sören Schalowski, and Heike Wiese. 2014. The KiezDeutsch Korpus (KiDKo) Release 1.0. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 3927–3934, Reykjavik, Iceland. European Language Resources Association (ELRA).