@inproceedings{street-etal-2010-like,
title = "Like Finding a Needle in a Haystack: Annotating the {A}merican National Corpus for Idiomatic Expressions",
author = "Street, Laura and
Michalov, Nathan and
Silverstein, Rachel and
Reynolds, Michael and
Ruela, Lurdes and
Flowers, Felicia and
Talucci, Angela and
Pereira, Priscilla and
Morgon, Gabriella and
Siegel, Samantha and
Barousse, Marci and
Anderson, Antequa and
Carroll, Tashom and
Feldman, Anna",
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/668_Paper.pdf",
abstract = "Our paper presents the details of a pilot study in which we tagged portions of the American National Corpus (ANC) for idioms composed of verb-noun constructions, prepositional phrases, and subordinate clauses. The three data sets we analyzed included 1,500-sentence samples from the spoken, the nonfiction, and the fiction portions of the ANC. Our paper provides the details of the tagset we developed, the motivation behind our choices, and the inter-annotator agreement measures we deemed appropriate for this task. In tagging the ANC for idiomatic expressions, our annotators achieved a high level of agreement ({\textgreater} .80) on the tags but a low level of agreement ({\textless} .00) on what constituted an idiom. These findings support the claim that identifying idiomatic and metaphorical expressions is a highly difficult and subjective task. In total, 135 idiom types and 154 idiom tokens were identified. Based on the total tokens found for each idiom class, we suggest that future research on idiom detection and idiom annotation include prepositional phrases as this class of idioms occurred frequently in the nonfiction and spoken samples of our corpus",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="street-etal-2010-like">
<titleInfo>
<title>Like Finding a Needle in a Haystack: Annotating the American National Corpus for Idiomatic Expressions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Street</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Michalov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Silverstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Reynolds</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lurdes</namePart>
<namePart type="family">Ruela</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felicia</namePart>
<namePart type="family">Flowers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Talucci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priscilla</namePart>
<namePart type="family">Pereira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriella</namePart>
<namePart type="family">Morgon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samantha</namePart>
<namePart type="family">Siegel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marci</namePart>
<namePart type="family">Barousse</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antequa</namePart>
<namePart type="family">Anderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tashom</namePart>
<namePart type="family">Carroll</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Feldman</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>Our paper presents the details of a pilot study in which we tagged portions of the American National Corpus (ANC) for idioms composed of verb-noun constructions, prepositional phrases, and subordinate clauses. The three data sets we analyzed included 1,500-sentence samples from the spoken, the nonfiction, and the fiction portions of the ANC. Our paper provides the details of the tagset we developed, the motivation behind our choices, and the inter-annotator agreement measures we deemed appropriate for this task. In tagging the ANC for idiomatic expressions, our annotators achieved a high level of agreement (\textgreater .80) on the tags but a low level of agreement (\textless .00) on what constituted an idiom. These findings support the claim that identifying idiomatic and metaphorical expressions is a highly difficult and subjective task. In total, 135 idiom types and 154 idiom tokens were identified. Based on the total tokens found for each idiom class, we suggest that future research on idiom detection and idiom annotation include prepositional phrases as this class of idioms occurred frequently in the nonfiction and spoken samples of our corpus</abstract>
<identifier type="citekey">street-etal-2010-like</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/668_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Like Finding a Needle in a Haystack: Annotating the American National Corpus for Idiomatic Expressions
%A Street, Laura
%A Michalov, Nathan
%A Silverstein, Rachel
%A Reynolds, Michael
%A Ruela, Lurdes
%A Flowers, Felicia
%A Talucci, Angela
%A Pereira, Priscilla
%A Morgon, Gabriella
%A Siegel, Samantha
%A Barousse, Marci
%A Anderson, Antequa
%A Carroll, Tashom
%A Feldman, Anna
%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 street-etal-2010-like
%X Our paper presents the details of a pilot study in which we tagged portions of the American National Corpus (ANC) for idioms composed of verb-noun constructions, prepositional phrases, and subordinate clauses. The three data sets we analyzed included 1,500-sentence samples from the spoken, the nonfiction, and the fiction portions of the ANC. Our paper provides the details of the tagset we developed, the motivation behind our choices, and the inter-annotator agreement measures we deemed appropriate for this task. In tagging the ANC for idiomatic expressions, our annotators achieved a high level of agreement (\textgreater .80) on the tags but a low level of agreement (\textless .00) on what constituted an idiom. These findings support the claim that identifying idiomatic and metaphorical expressions is a highly difficult and subjective task. In total, 135 idiom types and 154 idiom tokens were identified. Based on the total tokens found for each idiom class, we suggest that future research on idiom detection and idiom annotation include prepositional phrases as this class of idioms occurred frequently in the nonfiction and spoken samples of our corpus
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/668_Paper.pdf
Markdown (Informal)
[Like Finding a Needle in a Haystack: Annotating the American National Corpus for Idiomatic Expressions](http://www.lrec-conf.org/proceedings/lrec2010/pdf/668_Paper.pdf) (Street et al., LREC 2010)
ACL
- Laura Street, Nathan Michalov, Rachel Silverstein, Michael Reynolds, Lurdes Ruela, Felicia Flowers, Angela Talucci, Priscilla Pereira, Gabriella Morgon, Samantha Siegel, Marci Barousse, Antequa Anderson, Tashom Carroll, and Anna Feldman. 2010. Like Finding a Needle in a Haystack: Annotating the American National Corpus for Idiomatic Expressions. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).