@inproceedings{barbot-etal-2012-comparing,
title = "Comparing performance of different set-covering strategies for linguistic content optimization in speech corpora",
author = "Barbot, Nelly and
Boeffard, Olivier and
Delhay, Arnaud",
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/381_Paper.pdf",
pages = "969--974",
abstract = "Set covering algorithms are efficient tools for solving an optimal linguistic corpus reduction. The optimality of such a process is directly related to the descriptive features of the sentences of a reference corpus. This article suggests to verify experimentally the behaviour of three algorithms, a greedy approach and a lagrangian relaxation based one giving importance to rare events and a third one considering the Kullback-Liebler divergence between a reference and the ongoing distribution of events. The analysis of the content of the reduced corpora shows that the both first approaches stay the most effective to compress a corpus while guaranteeing a minimal content. The variant which minimises the Kullback-Liebler divergence guarantees a distribution of events close to a reference distribution as expected; however, the price for this solution is a much more important corpus. In the proposed experiments, we have also evaluated a mixed-approach considering a random complement to the smallest coverings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="barbot-etal-2012-comparing">
<titleInfo>
<title>Comparing performance of different set-covering strategies for linguistic content optimization in speech corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nelly</namePart>
<namePart type="family">Barbot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olivier</namePart>
<namePart type="family">Boeffard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arnaud</namePart>
<namePart type="family">Delhay</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>Set covering algorithms are efficient tools for solving an optimal linguistic corpus reduction. The optimality of such a process is directly related to the descriptive features of the sentences of a reference corpus. This article suggests to verify experimentally the behaviour of three algorithms, a greedy approach and a lagrangian relaxation based one giving importance to rare events and a third one considering the Kullback-Liebler divergence between a reference and the ongoing distribution of events. The analysis of the content of the reduced corpora shows that the both first approaches stay the most effective to compress a corpus while guaranteeing a minimal content. The variant which minimises the Kullback-Liebler divergence guarantees a distribution of events close to a reference distribution as expected; however, the price for this solution is a much more important corpus. In the proposed experiments, we have also evaluated a mixed-approach considering a random complement to the smallest coverings.</abstract>
<identifier type="citekey">barbot-etal-2012-comparing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/381_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>969</start>
<end>974</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparing performance of different set-covering strategies for linguistic content optimization in speech corpora
%A Barbot, Nelly
%A Boeffard, Olivier
%A Delhay, Arnaud
%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 barbot-etal-2012-comparing
%X Set covering algorithms are efficient tools for solving an optimal linguistic corpus reduction. The optimality of such a process is directly related to the descriptive features of the sentences of a reference corpus. This article suggests to verify experimentally the behaviour of three algorithms, a greedy approach and a lagrangian relaxation based one giving importance to rare events and a third one considering the Kullback-Liebler divergence between a reference and the ongoing distribution of events. The analysis of the content of the reduced corpora shows that the both first approaches stay the most effective to compress a corpus while guaranteeing a minimal content. The variant which minimises the Kullback-Liebler divergence guarantees a distribution of events close to a reference distribution as expected; however, the price for this solution is a much more important corpus. In the proposed experiments, we have also evaluated a mixed-approach considering a random complement to the smallest coverings.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/381_Paper.pdf
%P 969-974
Markdown (Informal)
[Comparing performance of different set-covering strategies for linguistic content optimization in speech corpora](http://www.lrec-conf.org/proceedings/lrec2012/pdf/381_Paper.pdf) (Barbot et al., LREC 2012)
ACL