@inproceedings{recasens-etal-2012-annotating,
title = "Annotating Near-Identity from Coreference Disagreements",
author = "Recasens, Marta and
Mart{\'\i}, M. Ant{\`o}nia and
Orasan, Constantin",
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/674_Paper.pdf",
pages = "165--172",
abstract = "We present an extension of the coreference annotation in the English NP4E and the Catalan AnCora-CA corpora with near-identity relations, which are borderline cases of coreference. The annotated subcorpora have 50K tokens each. Near-identity relations, as presented by Recasens et al. (2010; 2011), build upon the idea that identity is a continuum rather than an either/or relation, thus introducing a middle ground category to explain currently problematic cases. The first annotation effort that we describe shows that it is not possible to annotate near-identity explicitly because subjects are not fully aware of it. Therefore, our second annotation effort used an indirect method, and arrived at near-identity annotations by inference from the disagreements between five annotators who had only a two-alternative choice between coreference and non-coreference. The results show that whereas as little as 2-6{\%} of the relations were explicitly annotated as near-identity in the former effort, up to 12-16{\%} of the relations turned out to be near-identical following the indirect method of the latter effort.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="recasens-etal-2012-annotating">
<titleInfo>
<title>Annotating Near-Identity from Coreference Disagreements</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="family">Recasens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">M</namePart>
<namePart type="given">Antònia</namePart>
<namePart type="family">Martí</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantin</namePart>
<namePart type="family">Orasan</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>We present an extension of the coreference annotation in the English NP4E and the Catalan AnCora-CA corpora with near-identity relations, which are borderline cases of coreference. The annotated subcorpora have 50K tokens each. Near-identity relations, as presented by Recasens et al. (2010; 2011), build upon the idea that identity is a continuum rather than an either/or relation, thus introducing a middle ground category to explain currently problematic cases. The first annotation effort that we describe shows that it is not possible to annotate near-identity explicitly because subjects are not fully aware of it. Therefore, our second annotation effort used an indirect method, and arrived at near-identity annotations by inference from the disagreements between five annotators who had only a two-alternative choice between coreference and non-coreference. The results show that whereas as little as 2-6% of the relations were explicitly annotated as near-identity in the former effort, up to 12-16% of the relations turned out to be near-identical following the indirect method of the latter effort.</abstract>
<identifier type="citekey">recasens-etal-2012-annotating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/674_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>165</start>
<end>172</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Annotating Near-Identity from Coreference Disagreements
%A Recasens, Marta
%A Martí, M. Antònia
%A Orasan, Constantin
%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 recasens-etal-2012-annotating
%X We present an extension of the coreference annotation in the English NP4E and the Catalan AnCora-CA corpora with near-identity relations, which are borderline cases of coreference. The annotated subcorpora have 50K tokens each. Near-identity relations, as presented by Recasens et al. (2010; 2011), build upon the idea that identity is a continuum rather than an either/or relation, thus introducing a middle ground category to explain currently problematic cases. The first annotation effort that we describe shows that it is not possible to annotate near-identity explicitly because subjects are not fully aware of it. Therefore, our second annotation effort used an indirect method, and arrived at near-identity annotations by inference from the disagreements between five annotators who had only a two-alternative choice between coreference and non-coreference. The results show that whereas as little as 2-6% of the relations were explicitly annotated as near-identity in the former effort, up to 12-16% of the relations turned out to be near-identical following the indirect method of the latter effort.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/674_Paper.pdf
%P 165-172
Markdown (Informal)
[Annotating Near-Identity from Coreference Disagreements](http://www.lrec-conf.org/proceedings/lrec2012/pdf/674_Paper.pdf) (Recasens et al., LREC 2012)
ACL
- Marta Recasens, M. Antònia Martí, and Constantin Orasan. 2012. Annotating Near-Identity from Coreference Disagreements. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 165–172, Istanbul, Turkey. European Language Resources Association (ELRA).