@inproceedings{antunes-mendes-2014-evaluation,
title = "An evaluation of the role of statistical measures and frequency for {MWE} identification",
author = "Antunes, Sandra and
Mendes, Am{\'a}lia",
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/1197_Paper.pdf",
pages = "4046--4051",
abstract = "We report on an experiment to evaluate the role of statistical association measures and frequency for the identification of MWE. We base our evaluation on a lexicon of 14.000 MWE comprising different types of word combinations: collocations, nominal compounds, light verbs + predicate, idioms, etc. These MWE were manually validated from a list of n-grams extracted from a 50 million word corpus of Portuguese (a subcorpus of the Reference Corpus of Contemporary Portuguese), using several criteria: syntactic fixedness, idiomaticity, frequency and Mutual Information measure, although no threshold was established, either in terms of group frequency or MI. We report on MWE that were selected on the basis of their syntactic and semantics properties while the MI or both the MI and the frequency show low values, which would constitute difficult cases to establish a cutting point. We analyze the MI values of the MWE selected in our gold dataset and, for some specific cases, compare these values with two other statistical measures.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="antunes-mendes-2014-evaluation">
<titleInfo>
<title>An evaluation of the role of statistical measures and frequency for MWE identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Antunes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amália</namePart>
<namePart type="family">Mendes</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>We report on an experiment to evaluate the role of statistical association measures and frequency for the identification of MWE. We base our evaluation on a lexicon of 14.000 MWE comprising different types of word combinations: collocations, nominal compounds, light verbs + predicate, idioms, etc. These MWE were manually validated from a list of n-grams extracted from a 50 million word corpus of Portuguese (a subcorpus of the Reference Corpus of Contemporary Portuguese), using several criteria: syntactic fixedness, idiomaticity, frequency and Mutual Information measure, although no threshold was established, either in terms of group frequency or MI. We report on MWE that were selected on the basis of their syntactic and semantics properties while the MI or both the MI and the frequency show low values, which would constitute difficult cases to establish a cutting point. We analyze the MI values of the MWE selected in our gold dataset and, for some specific cases, compare these values with two other statistical measures.</abstract>
<identifier type="citekey">antunes-mendes-2014-evaluation</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1197_Paper.pdf</url>
</location>
<part>
<date>2014-may</date>
<extent unit="page">
<start>4046</start>
<end>4051</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An evaluation of the role of statistical measures and frequency for MWE identification
%A Antunes, Sandra
%A Mendes, Amália
%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 antunes-mendes-2014-evaluation
%X We report on an experiment to evaluate the role of statistical association measures and frequency for the identification of MWE. We base our evaluation on a lexicon of 14.000 MWE comprising different types of word combinations: collocations, nominal compounds, light verbs + predicate, idioms, etc. These MWE were manually validated from a list of n-grams extracted from a 50 million word corpus of Portuguese (a subcorpus of the Reference Corpus of Contemporary Portuguese), using several criteria: syntactic fixedness, idiomaticity, frequency and Mutual Information measure, although no threshold was established, either in terms of group frequency or MI. We report on MWE that were selected on the basis of their syntactic and semantics properties while the MI or both the MI and the frequency show low values, which would constitute difficult cases to establish a cutting point. We analyze the MI values of the MWE selected in our gold dataset and, for some specific cases, compare these values with two other statistical measures.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1197_Paper.pdf
%P 4046-4051
Markdown (Informal)
[An evaluation of the role of statistical measures and frequency for MWE identification](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1197_Paper.pdf) (Antunes & Mendes, LREC 2014)
ACL