@inproceedings{vivaldi-rodriguez-2004-automatically,
title = "Automatically Selecting Domain Markers for Terminology Extraction",
author = "Vivaldi, Jorge and
Rodr{\'\i}guez, Horacio",
editor = "Lino, Maria Teresa and
Xavier, Maria Francisca and
Ferreira, F{\'a}tima and
Costa, Rute and
Silva, Raquel",
booktitle = "Proceedings of the Fourth International Conference on Language Resources and Evaluation ({LREC}{'}04)",
month = may,
year = "2004",
address = "Lisbon, Portugal",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2004/pdf/348.pdf",
abstract = "Some approaches to automatic terminology extraction from corpora imply the use of existing semantic resources for guiding the detection of terms. Most of these systems exploit specialised resources, like UMLS in the medical domain, while a few try to take profit from general-purpose semantic resources, like EuroWordNet (EWN). As the term extraction task is clearly domain depending, in the case a general-purpose resource without specific domain information is used, we need a way of attaching domain information to the units of the resource. For big resources it is desirable that this semantic enrichment could be carried out automatically. Given a specific domain, our proposal aims to detect in EWN those units that can be considered as domain markers (DM). We can define a DM as an EWN entry whose attached strings belong to the domain, as well as the variants of all its descendents through the hyponymy relation. The procedure we propose in this paper is fully automatic and, a priori, domain-independent. The only external knowledge it uses is a set of terms, which is an external vocabulary, which is considered to have at least one sense belonging to the domain.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vivaldi-rodriguez-2004-automatically">
<titleInfo>
<title>Automatically Selecting Domain Markers for Terminology Extraction</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>2004-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Teresa</namePart>
<namePart type="family">Lino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Francisca</namePart>
<namePart type="family">Xavier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fátima</namePart>
<namePart type="family">Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rute</namePart>
<namePart type="family">Costa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Lisbon, Portugal</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Some approaches to automatic terminology extraction from corpora imply the use of existing semantic resources for guiding the detection of terms. Most of these systems exploit specialised resources, like UMLS in the medical domain, while a few try to take profit from general-purpose semantic resources, like EuroWordNet (EWN). As the term extraction task is clearly domain depending, in the case a general-purpose resource without specific domain information is used, we need a way of attaching domain information to the units of the resource. For big resources it is desirable that this semantic enrichment could be carried out automatically. Given a specific domain, our proposal aims to detect in EWN those units that can be considered as domain markers (DM). We can define a DM as an EWN entry whose attached strings belong to the domain, as well as the variants of all its descendents through the hyponymy relation. The procedure we propose in this paper is fully automatic and, a priori, domain-independent. The only external knowledge it uses is a set of terms, which is an external vocabulary, which is considered to have at least one sense belonging to the domain.</abstract>
<identifier type="citekey">vivaldi-rodriguez-2004-automatically</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2004/pdf/348.pdf</url>
</location>
<part>
<date>2004-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatically Selecting Domain Markers for Terminology Extraction
%A Vivaldi, Jorge
%A Rodríguez, Horacio
%Y Lino, Maria Teresa
%Y Xavier, Maria Francisca
%Y Ferreira, Fátima
%Y Costa, Rute
%Y Silva, Raquel
%S Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)
%D 2004
%8 May
%I European Language Resources Association (ELRA)
%C Lisbon, Portugal
%F vivaldi-rodriguez-2004-automatically
%X Some approaches to automatic terminology extraction from corpora imply the use of existing semantic resources for guiding the detection of terms. Most of these systems exploit specialised resources, like UMLS in the medical domain, while a few try to take profit from general-purpose semantic resources, like EuroWordNet (EWN). As the term extraction task is clearly domain depending, in the case a general-purpose resource without specific domain information is used, we need a way of attaching domain information to the units of the resource. For big resources it is desirable that this semantic enrichment could be carried out automatically. Given a specific domain, our proposal aims to detect in EWN those units that can be considered as domain markers (DM). We can define a DM as an EWN entry whose attached strings belong to the domain, as well as the variants of all its descendents through the hyponymy relation. The procedure we propose in this paper is fully automatic and, a priori, domain-independent. The only external knowledge it uses is a set of terms, which is an external vocabulary, which is considered to have at least one sense belonging to the domain.
%U http://www.lrec-conf.org/proceedings/lrec2004/pdf/348.pdf
Markdown (Informal)
[Automatically Selecting Domain Markers for Terminology Extraction](http://www.lrec-conf.org/proceedings/lrec2004/pdf/348.pdf) (Vivaldi & Rodríguez, LREC 2004)
ACL