@inproceedings{chevelu-etal-2008-comparing,
title = "Comparing Set-Covering Strategies for Optimal Corpus Design",
author = "Chevelu, Jonathan and
Barbot, Nelly and
Boeffard, Olivier and
Delhay, Arnaud",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/750_paper.pdf",
abstract = "This article is interested in the problem of the linguistic content of a speech corpus. Depending on the target task, the phonological and linguistic content of the corpus is controlled by collecting a set of sentences which covers a preset description of phonological attributes under the constraint of an overall duration as small as possible. This goal is classically achieved by greedy algorithms which however do not guarantee the optimality of the desired cover. In recent works, a lagrangian-based algorithm, called LamSCP, has been used to extract coverings of diphonemes from a large corpus in French, giving better results than a greedy algorithm. We propose to keep comparing both algorithms in terms of the shortest duration, stability and robustness by achieving multi-represented diphoneme or triphoneme covering. These coverings correspond to very large scale optimization problems, from a corpus in English. For each experiment, LamSCP improves the greedy results from 3.9 to 9.7 percent.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chevelu-etal-2008-comparing">
<titleInfo>
<title>Comparing Set-Covering Strategies for Optimal Corpus Design</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Chevelu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Stelios</namePart>
<namePart type="family">Piperidis</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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article is interested in the problem of the linguistic content of a speech corpus. Depending on the target task, the phonological and linguistic content of the corpus is controlled by collecting a set of sentences which covers a preset description of phonological attributes under the constraint of an overall duration as small as possible. This goal is classically achieved by greedy algorithms which however do not guarantee the optimality of the desired cover. In recent works, a lagrangian-based algorithm, called LamSCP, has been used to extract coverings of diphonemes from a large corpus in French, giving better results than a greedy algorithm. We propose to keep comparing both algorithms in terms of the shortest duration, stability and robustness by achieving multi-represented diphoneme or triphoneme covering. These coverings correspond to very large scale optimization problems, from a corpus in English. For each experiment, LamSCP improves the greedy results from 3.9 to 9.7 percent.</abstract>
<identifier type="citekey">chevelu-etal-2008-comparing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/750_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparing Set-Covering Strategies for Optimal Corpus Design
%A Chevelu, Jonathan
%A Barbot, Nelly
%A Boeffard, Olivier
%A Delhay, Arnaud
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F chevelu-etal-2008-comparing
%X This article is interested in the problem of the linguistic content of a speech corpus. Depending on the target task, the phonological and linguistic content of the corpus is controlled by collecting a set of sentences which covers a preset description of phonological attributes under the constraint of an overall duration as small as possible. This goal is classically achieved by greedy algorithms which however do not guarantee the optimality of the desired cover. In recent works, a lagrangian-based algorithm, called LamSCP, has been used to extract coverings of diphonemes from a large corpus in French, giving better results than a greedy algorithm. We propose to keep comparing both algorithms in terms of the shortest duration, stability and robustness by achieving multi-represented diphoneme or triphoneme covering. These coverings correspond to very large scale optimization problems, from a corpus in English. For each experiment, LamSCP improves the greedy results from 3.9 to 9.7 percent.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/750_paper.pdf
Markdown (Informal)
[Comparing Set-Covering Strategies for Optimal Corpus Design](http://www.lrec-conf.org/proceedings/lrec2008/pdf/750_paper.pdf) (Chevelu et al., LREC 2008)
ACL
- Jonathan Chevelu, Nelly Barbot, Olivier Boeffard, and Arnaud Delhay. 2008. Comparing Set-Covering Strategies for Optimal Corpus Design. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).