@inproceedings{vivaldi-etal-2012-using,
title = "Using {W}ikipedia to Validate the Terminology found in a Corpus of Basic Textbooks",
author = "Vivaldi, Jorge and
Cabrera-Diego, Luis Adri{\'a}n and
Sierra, Gerardo and
Pozzi, Mar{\'\i}a",
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/515_Paper.pdf",
pages = "3820--3827",
abstract = "A scientific vocabulary is a set of terms that designate scientific concepts. This set of lexical units can be used in several applications ranging from the development of terminological dictionaries and machine translation systems to the development of lexical databases and beyond. Even though automatic term recognition systems exist since the 80s, this process is still mainly done by hand, since it generally yields more accurate results, although not in less time and at a higher cost. Some of the reasons for this are the fairly low precision and recall results obtained, the domain dependence of existing tools and the lack of available semantic knowledge needed to validate these results. In this paper we present a method that uses Wikipedia as a semantic knowledge resource, to validate term candidates from a set of scientific text books used in the last three years of high school for mathematics, health education and ecology. The proposed method may be applied to any domain or language (assuming there is a minimal coverage by Wikipedia).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vivaldi-etal-2012-using">
<titleInfo>
<title>Using Wikipedia to Validate the Terminology found in a Corpus of Basic Textbooks</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">Luis</namePart>
<namePart type="given">Adrián</namePart>
<namePart type="family">Cabrera-Diego</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerardo</namePart>
<namePart type="family">Sierra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">María</namePart>
<namePart type="family">Pozzi</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>A scientific vocabulary is a set of terms that designate scientific concepts. This set of lexical units can be used in several applications ranging from the development of terminological dictionaries and machine translation systems to the development of lexical databases and beyond. Even though automatic term recognition systems exist since the 80s, this process is still mainly done by hand, since it generally yields more accurate results, although not in less time and at a higher cost. Some of the reasons for this are the fairly low precision and recall results obtained, the domain dependence of existing tools and the lack of available semantic knowledge needed to validate these results. In this paper we present a method that uses Wikipedia as a semantic knowledge resource, to validate term candidates from a set of scientific text books used in the last three years of high school for mathematics, health education and ecology. The proposed method may be applied to any domain or language (assuming there is a minimal coverage by Wikipedia).</abstract>
<identifier type="citekey">vivaldi-etal-2012-using</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/515_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3820</start>
<end>3827</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Wikipedia to Validate the Terminology found in a Corpus of Basic Textbooks
%A Vivaldi, Jorge
%A Cabrera-Diego, Luis Adrián
%A Sierra, Gerardo
%A Pozzi, María
%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 vivaldi-etal-2012-using
%X A scientific vocabulary is a set of terms that designate scientific concepts. This set of lexical units can be used in several applications ranging from the development of terminological dictionaries and machine translation systems to the development of lexical databases and beyond. Even though automatic term recognition systems exist since the 80s, this process is still mainly done by hand, since it generally yields more accurate results, although not in less time and at a higher cost. Some of the reasons for this are the fairly low precision and recall results obtained, the domain dependence of existing tools and the lack of available semantic knowledge needed to validate these results. In this paper we present a method that uses Wikipedia as a semantic knowledge resource, to validate term candidates from a set of scientific text books used in the last three years of high school for mathematics, health education and ecology. The proposed method may be applied to any domain or language (assuming there is a minimal coverage by Wikipedia).
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/515_Paper.pdf
%P 3820-3827
Markdown (Informal)
[Using Wikipedia to Validate the Terminology found in a Corpus of Basic Textbooks](http://www.lrec-conf.org/proceedings/lrec2012/pdf/515_Paper.pdf) (Vivaldi et al., LREC 2012)
ACL