@inproceedings{vivaldi-rodriguez-2010-finding,
title = "Finding Domain Terms using {W}ikipedia",
author = "Vivaldi, Jorge and
Rodr{\'\i}guez, Horacio",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/748_Paper.pdf",
abstract = "In this paper we present a new approach for obtaining the terminology of a given domain using the category and page structures of the Wikipedia in a language independent way. Our approach consists basically, for each domain, on navigating the Category graph of the Wikipedia starting from the root nodes associated to the domain. A heavy filtering mechanism is carried out for preventing as much as possible the inclusion of spurious categories. For each selected category all the pages belonging to it are then recovered and filtered. This procedure is iterate several times until achieving convergence. Both category names and page names are considered candidates to belong to the terminology of the domain. This approach has been applied to three broad coverage domains: astronomy, chemistry and medicine, and two languages, English and Spanish, showing a promising performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vivaldi-rodriguez-2010-finding">
<titleInfo>
<title>Finding Domain Terms using Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Vivaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Horacio</namePart>
<namePart type="family">Rodríguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we present a new approach for obtaining the terminology of a given domain using the category and page structures of the Wikipedia in a language independent way. Our approach consists basically, for each domain, on navigating the Category graph of the Wikipedia starting from the root nodes associated to the domain. A heavy filtering mechanism is carried out for preventing as much as possible the inclusion of spurious categories. For each selected category all the pages belonging to it are then recovered and filtered. This procedure is iterate several times until achieving convergence. Both category names and page names are considered candidates to belong to the terminology of the domain. This approach has been applied to three broad coverage domains: astronomy, chemistry and medicine, and two languages, English and Spanish, showing a promising performance.</abstract>
<identifier type="citekey">vivaldi-rodriguez-2010-finding</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/748_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Finding Domain Terms using Wikipedia
%A Vivaldi, Jorge
%A Rodríguez, Horacio
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F vivaldi-rodriguez-2010-finding
%X In this paper we present a new approach for obtaining the terminology of a given domain using the category and page structures of the Wikipedia in a language independent way. Our approach consists basically, for each domain, on navigating the Category graph of the Wikipedia starting from the root nodes associated to the domain. A heavy filtering mechanism is carried out for preventing as much as possible the inclusion of spurious categories. For each selected category all the pages belonging to it are then recovered and filtered. This procedure is iterate several times until achieving convergence. Both category names and page names are considered candidates to belong to the terminology of the domain. This approach has been applied to three broad coverage domains: astronomy, chemistry and medicine, and two languages, English and Spanish, showing a promising performance.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/748_Paper.pdf
Markdown (Informal)
[Finding Domain Terms using Wikipedia](http://www.lrec-conf.org/proceedings/lrec2010/pdf/748_Paper.pdf) (Vivaldi & Rodríguez, LREC 2010)
ACL
- Jorge Vivaldi and Horacio Rodríguez. 2010. Finding Domain Terms using Wikipedia. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).