@inproceedings{roder-etal-2014-n3,
title = "N{\mbox{$^3$}} - A Collection of Datasets for Named Entity Recognition and Disambiguation in the {NLP} Interchange Format",
author = {R{\"o}der, Michael and
Usbeck, Ricardo and
Hellmann, Sebastian and
Gerber, Daniel and
Both, Andreas},
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/856_Paper.pdf",
pages = "3529--3533",
abstract = "Extracting Linked Data following the Semantic Web principle from unstructured sources has become a key challenge for scientific research. Named Entity Recognition and Disambiguation are two basic operations in this extraction process. One step towards the realization of the Semantic Web vision and the development of highly accurate tools is the availability of data for validating the quality of processes for Named Entity Recognition and Disambiguation as well as for algorithm tuning. This article presents three novel, manually curated and annotated corpora (N3). All of them are based on a free license and stored in the NLP Interchange Format to leverage the Linked Data character of our datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="roder-etal-2014-n3">
<titleInfo>
<title>N³ - A Collection of Datasets for Named Entity Recognition and Disambiguation in the NLP Interchange Format</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Röder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Usbeck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Hellmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Gerber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Both</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>Extracting Linked Data following the Semantic Web principle from unstructured sources has become a key challenge for scientific research. Named Entity Recognition and Disambiguation are two basic operations in this extraction process. One step towards the realization of the Semantic Web vision and the development of highly accurate tools is the availability of data for validating the quality of processes for Named Entity Recognition and Disambiguation as well as for algorithm tuning. This article presents three novel, manually curated and annotated corpora (N3). All of them are based on a free license and stored in the NLP Interchange Format to leverage the Linked Data character of our datasets.</abstract>
<identifier type="citekey">roder-etal-2014-n3</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/856_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3529</start>
<end>3533</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T N³ - A Collection of Datasets for Named Entity Recognition and Disambiguation in the NLP Interchange Format
%A Röder, Michael
%A Usbeck, Ricardo
%A Hellmann, Sebastian
%A Gerber, Daniel
%A Both, Andreas
%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 roder-etal-2014-n3
%X Extracting Linked Data following the Semantic Web principle from unstructured sources has become a key challenge for scientific research. Named Entity Recognition and Disambiguation are two basic operations in this extraction process. One step towards the realization of the Semantic Web vision and the development of highly accurate tools is the availability of data for validating the quality of processes for Named Entity Recognition and Disambiguation as well as for algorithm tuning. This article presents three novel, manually curated and annotated corpora (N3). All of them are based on a free license and stored in the NLP Interchange Format to leverage the Linked Data character of our datasets.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/856_Paper.pdf
%P 3529-3533
Markdown (Informal)
[N³ - A Collection of Datasets for Named Entity Recognition and Disambiguation in the NLP Interchange Format](http://www.lrec-conf.org/proceedings/lrec2014/pdf/856_Paper.pdf) (Röder et al., LREC 2014)
ACL