@inproceedings{butters-ciravegna-2008-using,
title = "Using Similarity Metrics For Terminology Recognition",
author = "Butters, Jonathan and
Ciravegna, Fabio",
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/717_paper.pdf",
abstract = "In this paper we present an approach to terminology recognition whereby a sublanguage term (e.g. an aircraft engine component term extracted from a maintenance log) is matched to its corresponding term from a pre-defined list (such as a taxonomy representing the official break-down of the engine). Terminology recognition is addressed as a classification task whereby the extracted term is associated to one or more potential terms in the official description list via the application of string similarity metrics. The solution described in the paper uses dynamically computed similarity cut-off thresholds calculated on the basis of modeling a noise curve. Dissimilar string matches form a Gaussian distributed noise curve that can be identified and extracted leaving only mostly similar string matches. Dynamically calculated thresholds are preferable over fixed similarity thresholds as fixed thresholds are inherently imprecise, that is, there is no similarity boundary beyond which any two strings always describe the same concept.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="butters-ciravegna-2008-using">
<titleInfo>
<title>Using Similarity Metrics For Terminology Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Butters</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Ciravegna</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>In this paper we present an approach to terminology recognition whereby a sublanguage term (e.g. an aircraft engine component term extracted from a maintenance log) is matched to its corresponding term from a pre-defined list (such as a taxonomy representing the official break-down of the engine). Terminology recognition is addressed as a classification task whereby the extracted term is associated to one or more potential terms in the official description list via the application of string similarity metrics. The solution described in the paper uses dynamically computed similarity cut-off thresholds calculated on the basis of modeling a noise curve. Dissimilar string matches form a Gaussian distributed noise curve that can be identified and extracted leaving only mostly similar string matches. Dynamically calculated thresholds are preferable over fixed similarity thresholds as fixed thresholds are inherently imprecise, that is, there is no similarity boundary beyond which any two strings always describe the same concept.</abstract>
<identifier type="citekey">butters-ciravegna-2008-using</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/717_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Similarity Metrics For Terminology Recognition
%A Butters, Jonathan
%A Ciravegna, Fabio
%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 butters-ciravegna-2008-using
%X In this paper we present an approach to terminology recognition whereby a sublanguage term (e.g. an aircraft engine component term extracted from a maintenance log) is matched to its corresponding term from a pre-defined list (such as a taxonomy representing the official break-down of the engine). Terminology recognition is addressed as a classification task whereby the extracted term is associated to one or more potential terms in the official description list via the application of string similarity metrics. The solution described in the paper uses dynamically computed similarity cut-off thresholds calculated on the basis of modeling a noise curve. Dissimilar string matches form a Gaussian distributed noise curve that can be identified and extracted leaving only mostly similar string matches. Dynamically calculated thresholds are preferable over fixed similarity thresholds as fixed thresholds are inherently imprecise, that is, there is no similarity boundary beyond which any two strings always describe the same concept.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/717_paper.pdf
Markdown (Informal)
[Using Similarity Metrics For Terminology Recognition](http://www.lrec-conf.org/proceedings/lrec2008/pdf/717_paper.pdf) (Butters & Ciravegna, LREC 2008)
ACL
- Jonathan Butters and Fabio Ciravegna. 2008. Using Similarity Metrics For Terminology Recognition. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).