@inproceedings{benikova-etal-2014-nosta,
title = "{N}o{S}ta-{D} Named Entity Annotation for {G}erman: Guidelines and Dataset",
author = "Benikova, Darina and
Biemann, Chris and
Reznicek, Marc",
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/276_Paper.pdf",
pages = "2524--2531",
abstract = "We describe the annotation of a new dataset for German Named Entity Recognition (NER). The need for this dataset is motivated by licensing issues and consistency issues of existing datasets. We describe our approach to creating annotation guidelines based on linguistic and semantic considerations, and how we iteratively refined and tested them in the early stages of annotation in order to arrive at the largest publicly available dataset for German NER, consisting of over 31,000 manually annotated sentences (over 591,000 tokens) from German Wikipedia and German online news. We provide a number of statistics on the dataset, which indicate its high quality, and discuss legal aspects of distributing the data as a compilation of citations. The data is released under the permissive CC-BY license, and will be fully available for download in September 2014 after it has been used for the GermEval 2014 shared task on NER. We further provide the full annotation guidelines and links to the annotation tool used for the creation of this resource.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="benikova-etal-2014-nosta">
<titleInfo>
<title>NoSta-D Named Entity Annotation for German: Guidelines and Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Darina</namePart>
<namePart type="family">Benikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Biemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Reznicek</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>We describe the annotation of a new dataset for German Named Entity Recognition (NER). The need for this dataset is motivated by licensing issues and consistency issues of existing datasets. We describe our approach to creating annotation guidelines based on linguistic and semantic considerations, and how we iteratively refined and tested them in the early stages of annotation in order to arrive at the largest publicly available dataset for German NER, consisting of over 31,000 manually annotated sentences (over 591,000 tokens) from German Wikipedia and German online news. We provide a number of statistics on the dataset, which indicate its high quality, and discuss legal aspects of distributing the data as a compilation of citations. The data is released under the permissive CC-BY license, and will be fully available for download in September 2014 after it has been used for the GermEval 2014 shared task on NER. We further provide the full annotation guidelines and links to the annotation tool used for the creation of this resource.</abstract>
<identifier type="citekey">benikova-etal-2014-nosta</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/276_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2524</start>
<end>2531</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NoSta-D Named Entity Annotation for German: Guidelines and Dataset
%A Benikova, Darina
%A Biemann, Chris
%A Reznicek, Marc
%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 benikova-etal-2014-nosta
%X We describe the annotation of a new dataset for German Named Entity Recognition (NER). The need for this dataset is motivated by licensing issues and consistency issues of existing datasets. We describe our approach to creating annotation guidelines based on linguistic and semantic considerations, and how we iteratively refined and tested them in the early stages of annotation in order to arrive at the largest publicly available dataset for German NER, consisting of over 31,000 manually annotated sentences (over 591,000 tokens) from German Wikipedia and German online news. We provide a number of statistics on the dataset, which indicate its high quality, and discuss legal aspects of distributing the data as a compilation of citations. The data is released under the permissive CC-BY license, and will be fully available for download in September 2014 after it has been used for the GermEval 2014 shared task on NER. We further provide the full annotation guidelines and links to the annotation tool used for the creation of this resource.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/276_Paper.pdf
%P 2524-2531
Markdown (Informal)
[NoSta-D Named Entity Annotation for German: Guidelines and Dataset](http://www.lrec-conf.org/proceedings/lrec2014/pdf/276_Paper.pdf) (Benikova et al., LREC 2014)
ACL