@inproceedings{kafkas-etal-2012-calbc,
title = "{CALBC}: Releasing the Final Corpora",
author = "Kafkas, {\c{S}}enay and
Lewin, Ian and
Milward, David and
van Mulligen, Erik and
Kors, Jan and
Hahn, Udo and
Rebholz-Schuhmann, Dietrich",
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/827_Paper.pdf",
pages = "2923--2926",
abstract = "A number of gold standard corpora for named entity recognition are available to the public. However, the existing gold standard corpora are limited in size and semantic entity types. These usually lead to implementation of trained solutions (1) for a limited number of semantic entity types and (2) lacking in generalization capability. In order to overcome these problems, the CALBC project has aimed to automatically generate large scale corpora annotated with multiple semantic entity types in a community-wide manner based on the consensus of different named entity solutions. The generated corpus is called the silver standard corpus since the corpus generation process does not involve any manual curation. In this publication, we announce the release of the final CALBC corpora which include the silver standard corpus in different versions and several gold standard corpora for the further usage of the biomedical text mining community. The gold standard corpora are utilised to benchmark the methods used in the silver standard corpora generation process and released in a shared format. All the corpora are released in a shared format and accessible at www.calbc.eu.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kafkas-etal-2012-calbc">
<titleInfo>
<title>CALBC: Releasing the Final Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Şenay</namePart>
<namePart type="family">Kafkas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ian</namePart>
<namePart type="family">Lewin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Milward</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">van Mulligen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Kors</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Udo</namePart>
<namePart type="family">Hahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dietrich</namePart>
<namePart type="family">Rebholz-Schuhmann</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>A number of gold standard corpora for named entity recognition are available to the public. However, the existing gold standard corpora are limited in size and semantic entity types. These usually lead to implementation of trained solutions (1) for a limited number of semantic entity types and (2) lacking in generalization capability. In order to overcome these problems, the CALBC project has aimed to automatically generate large scale corpora annotated with multiple semantic entity types in a community-wide manner based on the consensus of different named entity solutions. The generated corpus is called the silver standard corpus since the corpus generation process does not involve any manual curation. In this publication, we announce the release of the final CALBC corpora which include the silver standard corpus in different versions and several gold standard corpora for the further usage of the biomedical text mining community. The gold standard corpora are utilised to benchmark the methods used in the silver standard corpora generation process and released in a shared format. All the corpora are released in a shared format and accessible at www.calbc.eu.</abstract>
<identifier type="citekey">kafkas-etal-2012-calbc</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/827_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2923</start>
<end>2926</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CALBC: Releasing the Final Corpora
%A Kafkas, Şenay
%A Lewin, Ian
%A Milward, David
%A van Mulligen, Erik
%A Kors, Jan
%A Hahn, Udo
%A Rebholz-Schuhmann, Dietrich
%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 kafkas-etal-2012-calbc
%X A number of gold standard corpora for named entity recognition are available to the public. However, the existing gold standard corpora are limited in size and semantic entity types. These usually lead to implementation of trained solutions (1) for a limited number of semantic entity types and (2) lacking in generalization capability. In order to overcome these problems, the CALBC project has aimed to automatically generate large scale corpora annotated with multiple semantic entity types in a community-wide manner based on the consensus of different named entity solutions. The generated corpus is called the silver standard corpus since the corpus generation process does not involve any manual curation. In this publication, we announce the release of the final CALBC corpora which include the silver standard corpus in different versions and several gold standard corpora for the further usage of the biomedical text mining community. The gold standard corpora are utilised to benchmark the methods used in the silver standard corpora generation process and released in a shared format. All the corpora are released in a shared format and accessible at www.calbc.eu.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/827_Paper.pdf
%P 2923-2926
Markdown (Informal)
[CALBC: Releasing the Final Corpora](http://www.lrec-conf.org/proceedings/lrec2012/pdf/827_Paper.pdf) (Kafkas et al., LREC 2012)
ACL
- Şenay Kafkas, Ian Lewin, David Milward, Erik van Mulligen, Jan Kors, Udo Hahn, and Dietrich Rebholz-Schuhmann. 2012. CALBC: Releasing the Final Corpora. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2923–2926, Istanbul, Turkey. European Language Resources Association (ELRA).