@inproceedings{zaninello-nissim-2010-creation,
title = "Creation of Lexical Resources for a Characterisation of Multiword Expressions in {I}talian",
author = "Zaninello, Andrea and
Nissim, Malvina",
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/567_Paper.pdf",
abstract = "The theoretical characterisation of multiword expressions (MWEs) is tightly connected to their actual occurrences in data and to their representation in lexical resources. We present three lexical resources for Italian MWEs, namely an electronic lexicon, a series of example corpora and a database of MWEs represented around morphosyntactic patterns. These resources are matched against, and created from, a very large web-derived corpus for Italian that spans across registers and domains. We can thus test expressions coded by lexicographers in a dictionary, thereby discarding unattested expressions, revisiting lexicographers's choices on the basis of frequency information, and at the same time creating an example sub-corpus for each entry. We organise MWEs on the basis of the morphosyntactic information obtained from the data in an electronic, flexible knowledge-base containing structured annotation exploitable for multiple purposes. We also suggest further work directions towards characterising MWEs by analysing the data organised in our database through lexico-semantic information available in WordNet or MultiWordNet-like resources, also in the perspective of expanding their set through the extraction of other similar compact expressions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zaninello-nissim-2010-creation">
<titleInfo>
<title>Creation of Lexical Resources for a Characterisation of Multiword Expressions in Italian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Zaninello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malvina</namePart>
<namePart type="family">Nissim</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 theoretical characterisation of multiword expressions (MWEs) is tightly connected to their actual occurrences in data and to their representation in lexical resources. We present three lexical resources for Italian MWEs, namely an electronic lexicon, a series of example corpora and a database of MWEs represented around morphosyntactic patterns. These resources are matched against, and created from, a very large web-derived corpus for Italian that spans across registers and domains. We can thus test expressions coded by lexicographers in a dictionary, thereby discarding unattested expressions, revisiting lexicographers’s choices on the basis of frequency information, and at the same time creating an example sub-corpus for each entry. We organise MWEs on the basis of the morphosyntactic information obtained from the data in an electronic, flexible knowledge-base containing structured annotation exploitable for multiple purposes. We also suggest further work directions towards characterising MWEs by analysing the data organised in our database through lexico-semantic information available in WordNet or MultiWordNet-like resources, also in the perspective of expanding their set through the extraction of other similar compact expressions.</abstract>
<identifier type="citekey">zaninello-nissim-2010-creation</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/567_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Creation of Lexical Resources for a Characterisation of Multiword Expressions in Italian
%A Zaninello, Andrea
%A Nissim, Malvina
%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 zaninello-nissim-2010-creation
%X The theoretical characterisation of multiword expressions (MWEs) is tightly connected to their actual occurrences in data and to their representation in lexical resources. We present three lexical resources for Italian MWEs, namely an electronic lexicon, a series of example corpora and a database of MWEs represented around morphosyntactic patterns. These resources are matched against, and created from, a very large web-derived corpus for Italian that spans across registers and domains. We can thus test expressions coded by lexicographers in a dictionary, thereby discarding unattested expressions, revisiting lexicographers’s choices on the basis of frequency information, and at the same time creating an example sub-corpus for each entry. We organise MWEs on the basis of the morphosyntactic information obtained from the data in an electronic, flexible knowledge-base containing structured annotation exploitable for multiple purposes. We also suggest further work directions towards characterising MWEs by analysing the data organised in our database through lexico-semantic information available in WordNet or MultiWordNet-like resources, also in the perspective of expanding their set through the extraction of other similar compact expressions.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/567_Paper.pdf
Markdown (Informal)
[Creation of Lexical Resources for a Characterisation of Multiword Expressions in Italian](http://www.lrec-conf.org/proceedings/lrec2010/pdf/567_Paper.pdf) (Zaninello & Nissim, LREC 2010)
ACL