@inproceedings{castilho-etal-2012-corpus,
title = "{C}orpus+{W}ord{N}et thesaurus generation for ontology enriching",
author = "Castilho, Fernando and
Granada, Roger and
Meneghetti, Breno and
Carvalho, Leonardo and
Vieira, Renata",
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/1062_Paper.pdf",
pages = "3463--3467",
abstract = "This paper presents a model to enrich an ontology with a thesaurus based on a domain corpus and WordNet. The model is applied to the data privacy domain and the initial domain resources comprise a data privacy ontology, a corpus of privacy laws, regulations and guidelines for projects. Based on these resources, a thesaurus is automatically generated. The thesaurus seeds are composed by the ontology concepts. For these seeds similar terms are extracted from the corpus using known thesaurus generation methods. A filtering process searches for semantic relations between seeds and similar terms within WordNet. As a result, these semantic relations are used to expand the ontology with relations between them and related terms in the corpus. The resulting resource is a hierarchical structure that can help on the ontology investigation and maintenance. The results allow the investigation of the domain knowledge with the support of semantic relations not present on the original ontology.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="castilho-etal-2012-corpus">
<titleInfo>
<title>Corpus+WordNet thesaurus generation for ontology enriching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Castilho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roger</namePart>
<namePart type="family">Granada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Breno</namePart>
<namePart type="family">Meneghetti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonardo</namePart>
<namePart type="family">Carvalho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Renata</namePart>
<namePart type="family">Vieira</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>This paper presents a model to enrich an ontology with a thesaurus based on a domain corpus and WordNet. The model is applied to the data privacy domain and the initial domain resources comprise a data privacy ontology, a corpus of privacy laws, regulations and guidelines for projects. Based on these resources, a thesaurus is automatically generated. The thesaurus seeds are composed by the ontology concepts. For these seeds similar terms are extracted from the corpus using known thesaurus generation methods. A filtering process searches for semantic relations between seeds and similar terms within WordNet. As a result, these semantic relations are used to expand the ontology with relations between them and related terms in the corpus. The resulting resource is a hierarchical structure that can help on the ontology investigation and maintenance. The results allow the investigation of the domain knowledge with the support of semantic relations not present on the original ontology.</abstract>
<identifier type="citekey">castilho-etal-2012-corpus</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/1062_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3463</start>
<end>3467</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Corpus+WordNet thesaurus generation for ontology enriching
%A Castilho, Fernando
%A Granada, Roger
%A Meneghetti, Breno
%A Carvalho, Leonardo
%A Vieira, Renata
%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 castilho-etal-2012-corpus
%X This paper presents a model to enrich an ontology with a thesaurus based on a domain corpus and WordNet. The model is applied to the data privacy domain and the initial domain resources comprise a data privacy ontology, a corpus of privacy laws, regulations and guidelines for projects. Based on these resources, a thesaurus is automatically generated. The thesaurus seeds are composed by the ontology concepts. For these seeds similar terms are extracted from the corpus using known thesaurus generation methods. A filtering process searches for semantic relations between seeds and similar terms within WordNet. As a result, these semantic relations are used to expand the ontology with relations between them and related terms in the corpus. The resulting resource is a hierarchical structure that can help on the ontology investigation and maintenance. The results allow the investigation of the domain knowledge with the support of semantic relations not present on the original ontology.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/1062_Paper.pdf
%P 3463-3467
Markdown (Informal)
[Corpus+WordNet thesaurus generation for ontology enriching](http://www.lrec-conf.org/proceedings/lrec2012/pdf/1062_Paper.pdf) (Castilho et al., LREC 2012)
ACL
- Fernando Castilho, Roger Granada, Breno Meneghetti, Leonardo Carvalho, and Renata Vieira. 2012. Corpus+WordNet thesaurus generation for ontology enriching. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 3463–3467, Istanbul, Turkey. European Language Resources Association (ELRA).