@inproceedings{ibekwe-sanjuan-2006-task,
title = "A task-oriented framework for evaluating theme detection systems: A discussion paper",
author = "Ibekwe-Sanjuan, Fidelia",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/678_pdf.pdf",
abstract = "This paper discusses the inherent difficulties in evaluating systems for theme detection. Such systems are based essentially on unsupervised clustering aiming to discover the underlying structure in a corpus of texts. As the structures are precisely unknown beforehand, it is difficult to devise a satisfactory evaluation protocol. Several problems are posed by cluster evaluation: determining the optimal number of clusters, cluster content evaluation, topology of the discovered structure. Each of these problems has been studied separately but some of the proposed metrics portray significant flaws. Moreover, no benchmark has been commonly agreed upon. Finally, it is necessary to distinguish between task-oriented and activity-oriented evaluation as the two frameworks imply different evaluation protocols. Possible solutions to the activity-oriented evaluation can be sought from the data and text mining communities.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ibekwe-sanjuan-2006-task">
<titleInfo>
<title>A task-oriented framework for evaluating theme detection systems: A discussion paper</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fidelia</namePart>
<namePart type="family">Ibekwe-Sanjuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper discusses the inherent difficulties in evaluating systems for theme detection. Such systems are based essentially on unsupervised clustering aiming to discover the underlying structure in a corpus of texts. As the structures are precisely unknown beforehand, it is difficult to devise a satisfactory evaluation protocol. Several problems are posed by cluster evaluation: determining the optimal number of clusters, cluster content evaluation, topology of the discovered structure. Each of these problems has been studied separately but some of the proposed metrics portray significant flaws. Moreover, no benchmark has been commonly agreed upon. Finally, it is necessary to distinguish between task-oriented and activity-oriented evaluation as the two frameworks imply different evaluation protocols. Possible solutions to the activity-oriented evaluation can be sought from the data and text mining communities.</abstract>
<identifier type="citekey">ibekwe-sanjuan-2006-task</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/678_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A task-oriented framework for evaluating theme detection systems: A discussion paper
%A Ibekwe-Sanjuan, Fidelia
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F ibekwe-sanjuan-2006-task
%X This paper discusses the inherent difficulties in evaluating systems for theme detection. Such systems are based essentially on unsupervised clustering aiming to discover the underlying structure in a corpus of texts. As the structures are precisely unknown beforehand, it is difficult to devise a satisfactory evaluation protocol. Several problems are posed by cluster evaluation: determining the optimal number of clusters, cluster content evaluation, topology of the discovered structure. Each of these problems has been studied separately but some of the proposed metrics portray significant flaws. Moreover, no benchmark has been commonly agreed upon. Finally, it is necessary to distinguish between task-oriented and activity-oriented evaluation as the two frameworks imply different evaluation protocols. Possible solutions to the activity-oriented evaluation can be sought from the data and text mining communities.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/678_pdf.pdf
Markdown (Informal)
[A task-oriented framework for evaluating theme detection systems: A discussion paper](http://www.lrec-conf.org/proceedings/lrec2006/pdf/678_pdf.pdf) (Ibekwe-Sanjuan, LREC 2006)
ACL