@inproceedings{wang-etal-2012-evaluation,
title = "Evaluation of Unsupervised Information Extraction",
author = "Wang, Wei and
Besan{\c{c}}on, Romaric and
Ferret, Olivier and
Grau, Brigitte",
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/553_Paper.pdf",
pages = "552--558",
abstract = "Unsupervised methods gain more and more attention nowadays in information extraction area, which allows to design more open extraction systems. In the domain of unsupervised information extraction, clustering methods are of particular importance. However, evaluating the results of clustering remains difficult at a large scale, especially in the absence of reliable reference. On the basis of our experiments on unsupervised relation extraction, we first discuss in this article how to evaluate clustering quality without a reference by relying on internal measures. Then we propose a method, supported by a dedicated annotation tool, for building a set of reference clusters of relations from a corpus. Moreover, we apply it to our experimental framework and illustrate in this way how to build a significant reference for unsupervised relation extraction, more precisely made of 80 clusters gathering more than 4,000 relation instances, in a short time. Finally, we present how such reference is exploited for the evaluation of clustering with external measures and analyze the results of the application of these measures to the clusters of relations produced by our unsupervised relation extraction system.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2012-evaluation">
<titleInfo>
<title>Evaluation of Unsupervised Information Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Romaric</namePart>
<namePart type="family">Besançon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olivier</namePart>
<namePart type="family">Ferret</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brigitte</namePart>
<namePart type="family">Grau</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>Unsupervised methods gain more and more attention nowadays in information extraction area, which allows to design more open extraction systems. In the domain of unsupervised information extraction, clustering methods are of particular importance. However, evaluating the results of clustering remains difficult at a large scale, especially in the absence of reliable reference. On the basis of our experiments on unsupervised relation extraction, we first discuss in this article how to evaluate clustering quality without a reference by relying on internal measures. Then we propose a method, supported by a dedicated annotation tool, for building a set of reference clusters of relations from a corpus. Moreover, we apply it to our experimental framework and illustrate in this way how to build a significant reference for unsupervised relation extraction, more precisely made of 80 clusters gathering more than 4,000 relation instances, in a short time. Finally, we present how such reference is exploited for the evaluation of clustering with external measures and analyze the results of the application of these measures to the clusters of relations produced by our unsupervised relation extraction system.</abstract>
<identifier type="citekey">wang-etal-2012-evaluation</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/553_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>552</start>
<end>558</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluation of Unsupervised Information Extraction
%A Wang, Wei
%A Besançon, Romaric
%A Ferret, Olivier
%A Grau, Brigitte
%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 wang-etal-2012-evaluation
%X Unsupervised methods gain more and more attention nowadays in information extraction area, which allows to design more open extraction systems. In the domain of unsupervised information extraction, clustering methods are of particular importance. However, evaluating the results of clustering remains difficult at a large scale, especially in the absence of reliable reference. On the basis of our experiments on unsupervised relation extraction, we first discuss in this article how to evaluate clustering quality without a reference by relying on internal measures. Then we propose a method, supported by a dedicated annotation tool, for building a set of reference clusters of relations from a corpus. Moreover, we apply it to our experimental framework and illustrate in this way how to build a significant reference for unsupervised relation extraction, more precisely made of 80 clusters gathering more than 4,000 relation instances, in a short time. Finally, we present how such reference is exploited for the evaluation of clustering with external measures and analyze the results of the application of these measures to the clusters of relations produced by our unsupervised relation extraction system.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/553_Paper.pdf
%P 552-558
Markdown (Informal)
[Evaluation of Unsupervised Information Extraction](http://www.lrec-conf.org/proceedings/lrec2012/pdf/553_Paper.pdf) (Wang et al., LREC 2012)
ACL
- Wei Wang, Romaric Besançon, Olivier Ferret, and Brigitte Grau. 2012. Evaluation of Unsupervised Information Extraction. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 552–558, Istanbul, Turkey. European Language Resources Association (ELRA).