@inproceedings{sporleder-etal-2010-idioms,
title = "Idioms in Context: The {IDIX} Corpus",
author = "Sporleder, Caroline and
Li, Linlin and
Gorinski, Philip and
Koch, Xaver",
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/618_Paper.pdf",
abstract = "Idioms and other figuratively used expressions pose considerable problems to natural language processing applications because they are very frequent and often behave idiosyncratically. Consequently, there has been much research on the automatic detection and extraction of idiomatic expressions. Most studies focus on type-based idiom detection, i.e., distinguishing whether a given expression can (potentially) be used idiomatically. However, many expressions such as ''``break the ice'''' can have both literal and non-literal readings and need to be disambiguated in a given context (token-based detection). So far relatively few approaches have attempted context-based idiom detection. One reason for this may be that few annotated resources are available that disambiguate expressions in context. With the IDIX corpus, we aim to address this. IDIX is available as an add-on to the BNC and disambiguates different usages of a subset of idioms. We believe that this resource will be useful both for linguistic and computational linguistic studies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sporleder-etal-2010-idioms">
<titleInfo>
<title>Idioms in Context: The IDIX Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Caroline</namePart>
<namePart type="family">Sporleder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linlin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philip</namePart>
<namePart type="family">Gorinski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xaver</namePart>
<namePart type="family">Koch</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>Idioms and other figuratively used expressions pose considerable problems to natural language processing applications because they are very frequent and often behave idiosyncratically. Consequently, there has been much research on the automatic detection and extraction of idiomatic expressions. Most studies focus on type-based idiom detection, i.e., distinguishing whether a given expression can (potentially) be used idiomatically. However, many expressions such as ”“break the ice”” can have both literal and non-literal readings and need to be disambiguated in a given context (token-based detection). So far relatively few approaches have attempted context-based idiom detection. One reason for this may be that few annotated resources are available that disambiguate expressions in context. With the IDIX corpus, we aim to address this. IDIX is available as an add-on to the BNC and disambiguates different usages of a subset of idioms. We believe that this resource will be useful both for linguistic and computational linguistic studies.</abstract>
<identifier type="citekey">sporleder-etal-2010-idioms</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/618_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Idioms in Context: The IDIX Corpus
%A Sporleder, Caroline
%A Li, Linlin
%A Gorinski, Philip
%A Koch, Xaver
%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 sporleder-etal-2010-idioms
%X Idioms and other figuratively used expressions pose considerable problems to natural language processing applications because they are very frequent and often behave idiosyncratically. Consequently, there has been much research on the automatic detection and extraction of idiomatic expressions. Most studies focus on type-based idiom detection, i.e., distinguishing whether a given expression can (potentially) be used idiomatically. However, many expressions such as ”“break the ice”” can have both literal and non-literal readings and need to be disambiguated in a given context (token-based detection). So far relatively few approaches have attempted context-based idiom detection. One reason for this may be that few annotated resources are available that disambiguate expressions in context. With the IDIX corpus, we aim to address this. IDIX is available as an add-on to the BNC and disambiguates different usages of a subset of idioms. We believe that this resource will be useful both for linguistic and computational linguistic studies.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/618_Paper.pdf
Markdown (Informal)
[Idioms in Context: The IDIX Corpus](http://www.lrec-conf.org/proceedings/lrec2010/pdf/618_Paper.pdf) (Sporleder et al., LREC 2010)
ACL
- Caroline Sporleder, Linlin Li, Philip Gorinski, and Xaver Koch. 2010. Idioms in Context: The IDIX Corpus. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).