@inproceedings{vanopstal-etal-2010-towards,
title = "Towards a Learning Approach for Abbreviation Detection and Resolution.",
author = "Vanopstal, Klaar and
Desmet, Bart and
Hoste, V{\'e}ronique",
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/737_Paper.pdf",
abstract = "The explosion of biomedical literature and with it the -uncontrolled- creation of abbreviations presents some special challenges for both human readers and computer applications. We developed an annotated corpus of Dutch medical text, and experimented with two approaches to abbreviation detection and resolution. Our corpus is composed of abstracts from two medical journals from the Low Countries in which approximately 65 percent (NTvG) and 48 percent (TvG) of the abbreviations have a corresponding full form in the abstract. Our first approach, a pattern-based system, consists of two steps: abbreviation detection and definition matching. This system has an average F-score of 0.82 for the detection of both defined and undefined abbreviations and an average F-score of 0.77 was obtained for the definitions. For our second approach, an SVM-based classifier was used on the preprocessed data sets, leading to an average F-score of 0.93 for the abbreviations; for the definitions an average F-score of 0.82 was obtained.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vanopstal-etal-2010-towards">
<titleInfo>
<title>Towards a Learning Approach for Abbreviation Detection and Resolution.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Klaar</namePart>
<namePart type="family">Vanopstal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bart</namePart>
<namePart type="family">Desmet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Véronique</namePart>
<namePart type="family">Hoste</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>The explosion of biomedical literature and with it the -uncontrolled- creation of abbreviations presents some special challenges for both human readers and computer applications. We developed an annotated corpus of Dutch medical text, and experimented with two approaches to abbreviation detection and resolution. Our corpus is composed of abstracts from two medical journals from the Low Countries in which approximately 65 percent (NTvG) and 48 percent (TvG) of the abbreviations have a corresponding full form in the abstract. Our first approach, a pattern-based system, consists of two steps: abbreviation detection and definition matching. This system has an average F-score of 0.82 for the detection of both defined and undefined abbreviations and an average F-score of 0.77 was obtained for the definitions. For our second approach, an SVM-based classifier was used on the preprocessed data sets, leading to an average F-score of 0.93 for the abbreviations; for the definitions an average F-score of 0.82 was obtained.</abstract>
<identifier type="citekey">vanopstal-etal-2010-towards</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/737_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards a Learning Approach for Abbreviation Detection and Resolution.
%A Vanopstal, Klaar
%A Desmet, Bart
%A Hoste, Véronique
%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 vanopstal-etal-2010-towards
%X The explosion of biomedical literature and with it the -uncontrolled- creation of abbreviations presents some special challenges for both human readers and computer applications. We developed an annotated corpus of Dutch medical text, and experimented with two approaches to abbreviation detection and resolution. Our corpus is composed of abstracts from two medical journals from the Low Countries in which approximately 65 percent (NTvG) and 48 percent (TvG) of the abbreviations have a corresponding full form in the abstract. Our first approach, a pattern-based system, consists of two steps: abbreviation detection and definition matching. This system has an average F-score of 0.82 for the detection of both defined and undefined abbreviations and an average F-score of 0.77 was obtained for the definitions. For our second approach, an SVM-based classifier was used on the preprocessed data sets, leading to an average F-score of 0.93 for the abbreviations; for the definitions an average F-score of 0.82 was obtained.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/737_Paper.pdf
Markdown (Informal)
[Towards a Learning Approach for Abbreviation Detection and Resolution.](http://www.lrec-conf.org/proceedings/lrec2010/pdf/737_Paper.pdf) (Vanopstal et al., LREC 2010)
ACL