@inproceedings{schneider-etal-2014-comprehensive,
title = "Comprehensive Annotation of Multiword Expressions in a Social Web Corpus",
author = "Schneider, Nathan and
Onuffer, Spencer and
Kazour, Nora and
Danchik, Emily and
Mordowanec, Michael T. and
Conrad, Henrietta and
Smith, Noah A.",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/521_Paper.pdf",
pages = "455--461",
abstract = "Multiword expressions (MWEs) are quite frequent in languages such as English, but their diversity, the scarcity of individual MWE types, and contextual ambiguity have presented obstacles to corpus-based studies and NLP systems addressing them as a class. Here we advocate for a comprehensive annotation approach: proceeding sentence by sentence, our annotators manually group tokens into MWEs according to guidelines that cover a broad range of multiword phenomena. Under this scheme, we have fully annotated an English web corpus for multiword expressions, including those containing gaps.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schneider-etal-2014-comprehensive">
<titleInfo>
<title>Comprehensive Annotation of Multiword Expressions in a Social Web Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Spencer</namePart>
<namePart type="family">Onuffer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Kazour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Danchik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Mordowanec</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henrietta</namePart>
<namePart type="family">Conrad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noah</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multiword expressions (MWEs) are quite frequent in languages such as English, but their diversity, the scarcity of individual MWE types, and contextual ambiguity have presented obstacles to corpus-based studies and NLP systems addressing them as a class. Here we advocate for a comprehensive annotation approach: proceeding sentence by sentence, our annotators manually group tokens into MWEs according to guidelines that cover a broad range of multiword phenomena. Under this scheme, we have fully annotated an English web corpus for multiword expressions, including those containing gaps.</abstract>
<identifier type="citekey">schneider-etal-2014-comprehensive</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/521_Paper.pdf</url>
</location>
<part>
<date>2014-may</date>
<extent unit="page">
<start>455</start>
<end>461</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comprehensive Annotation of Multiword Expressions in a Social Web Corpus
%A Schneider, Nathan
%A Onuffer, Spencer
%A Kazour, Nora
%A Danchik, Emily
%A Mordowanec, Michael T.
%A Conrad, Henrietta
%A Smith, Noah A.
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 may
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F schneider-etal-2014-comprehensive
%X Multiword expressions (MWEs) are quite frequent in languages such as English, but their diversity, the scarcity of individual MWE types, and contextual ambiguity have presented obstacles to corpus-based studies and NLP systems addressing them as a class. Here we advocate for a comprehensive annotation approach: proceeding sentence by sentence, our annotators manually group tokens into MWEs according to guidelines that cover a broad range of multiword phenomena. Under this scheme, we have fully annotated an English web corpus for multiword expressions, including those containing gaps.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/521_Paper.pdf
%P 455-461
Markdown (Informal)
[Comprehensive Annotation of Multiword Expressions in a Social Web Corpus](http://www.lrec-conf.org/proceedings/lrec2014/pdf/521_Paper.pdf) (Schneider et al., LREC 2014)
ACL
- Nathan Schneider, Spencer Onuffer, Nora Kazour, Emily Danchik, Michael T. Mordowanec, Henrietta Conrad, and Noah A. Smith. 2014. Comprehensive Annotation of Multiword Expressions in a Social Web Corpus. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 455–461, Reykjavik, Iceland. European Language Resources Association (ELRA).