@inproceedings{biemann-2012-turk,
title = "Turk Bootstrap Word Sense Inventory 2.0: A Large-Scale Resource for Lexical Substitution",
author = "Biemann, Chris",
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/252_Paper.pdf",
pages = "4038--4042",
abstract = "This paper presents the Turk Bootstrap Word Sense Inventory (TWSI) 2.0. This lexical resource, created by a crowdsourcing process using Amazon Mechanical Turk (\url{http://www.mturk.com}), encompasses a sense inventory for lexical substitution for 1,012 highly frequent English common nouns. Along with each sense, a large number of sense-annotated occurrences in context are given, as well as a weighted list of substitutions. Sense distinctions are not motivated by lexicographic considerations, but driven by substitutability: two usages belong to the same sense if their substitutions overlap considerably. After laying out the need for such a resource, the data is characterized in terms of organization and quantity. Then, we briefly describe how this data was used to create a system for lexical substitutions. Training a supervised lexical substitution system on a smaller version of the resource resulted in well over 90{\%} acceptability for lexical substitutions provided by the system. Thus, this resource can be used to set up reliable, enabling technologies for semantic natural language processing (NLP), some of which we discuss briefly.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="biemann-2012-turk">
<titleInfo>
<title>Turk Bootstrap Word Sense Inventory 2.0: A Large-Scale Resource for Lexical Substitution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Biemann</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>This paper presents the Turk Bootstrap Word Sense Inventory (TWSI) 2.0. This lexical resource, created by a crowdsourcing process using Amazon Mechanical Turk (http://www.mturk.com), encompasses a sense inventory for lexical substitution for 1,012 highly frequent English common nouns. Along with each sense, a large number of sense-annotated occurrences in context are given, as well as a weighted list of substitutions. Sense distinctions are not motivated by lexicographic considerations, but driven by substitutability: two usages belong to the same sense if their substitutions overlap considerably. After laying out the need for such a resource, the data is characterized in terms of organization and quantity. Then, we briefly describe how this data was used to create a system for lexical substitutions. Training a supervised lexical substitution system on a smaller version of the resource resulted in well over 90% acceptability for lexical substitutions provided by the system. Thus, this resource can be used to set up reliable, enabling technologies for semantic natural language processing (NLP), some of which we discuss briefly.</abstract>
<identifier type="citekey">biemann-2012-turk</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/252_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>4038</start>
<end>4042</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Turk Bootstrap Word Sense Inventory 2.0: A Large-Scale Resource for Lexical Substitution
%A Biemann, Chris
%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 biemann-2012-turk
%X This paper presents the Turk Bootstrap Word Sense Inventory (TWSI) 2.0. This lexical resource, created by a crowdsourcing process using Amazon Mechanical Turk (http://www.mturk.com), encompasses a sense inventory for lexical substitution for 1,012 highly frequent English common nouns. Along with each sense, a large number of sense-annotated occurrences in context are given, as well as a weighted list of substitutions. Sense distinctions are not motivated by lexicographic considerations, but driven by substitutability: two usages belong to the same sense if their substitutions overlap considerably. After laying out the need for such a resource, the data is characterized in terms of organization and quantity. Then, we briefly describe how this data was used to create a system for lexical substitutions. Training a supervised lexical substitution system on a smaller version of the resource resulted in well over 90% acceptability for lexical substitutions provided by the system. Thus, this resource can be used to set up reliable, enabling technologies for semantic natural language processing (NLP), some of which we discuss briefly.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/252_Paper.pdf
%P 4038-4042
Markdown (Informal)
[Turk Bootstrap Word Sense Inventory 2.0: A Large-Scale Resource for Lexical Substitution](http://www.lrec-conf.org/proceedings/lrec2012/pdf/252_Paper.pdf) (Biemann, LREC 2012)
ACL