@inproceedings{ramisch-etal-2010-mwetoolkit,
title = "mwetoolkit: a Framework for Multiword Expression Identification",
author = "Ramisch, Carlos and
Villavicencio, Aline and
Boitet, Christian",
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/803_Paper.pdf",
abstract = "This paper presents the Multiword Expression Toolkit (mwetoolkit), an environment for type and language-independent MWE identification from corpora. The mwetoolkit provides a targeted list of MWE candidates, extracted and filtered according to a number of user-defined criteria and a set of standard statistical association measures. For generating corpus counts, the toolkit provides both a corpus indexation facility and a tool for integration with web search engines, while for evaluation, it provides validation and annotation facilities. The mwetoolkit also allows easy integration with a machine learning tool for the creation and application of supervised MWE extraction models if annotated data is available. In our experiment, the mwetoolkit was tested and evaluated in the context of MWE extraction in the biomedical domain. Our preliminary results show that the toolkit performs better than other approaches, especially concerning recall. Moreover, this first version can also be extended in several ways in order to improve the quality of the results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ramisch-etal-2010-mwetoolkit">
<titleInfo>
<title>mwetoolkit: a Framework for Multiword Expression Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Ramisch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Boitet</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>This paper presents the Multiword Expression Toolkit (mwetoolkit), an environment for type and language-independent MWE identification from corpora. The mwetoolkit provides a targeted list of MWE candidates, extracted and filtered according to a number of user-defined criteria and a set of standard statistical association measures. For generating corpus counts, the toolkit provides both a corpus indexation facility and a tool for integration with web search engines, while for evaluation, it provides validation and annotation facilities. The mwetoolkit also allows easy integration with a machine learning tool for the creation and application of supervised MWE extraction models if annotated data is available. In our experiment, the mwetoolkit was tested and evaluated in the context of MWE extraction in the biomedical domain. Our preliminary results show that the toolkit performs better than other approaches, especially concerning recall. Moreover, this first version can also be extended in several ways in order to improve the quality of the results.</abstract>
<identifier type="citekey">ramisch-etal-2010-mwetoolkit</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/803_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T mwetoolkit: a Framework for Multiword Expression Identification
%A Ramisch, Carlos
%A Villavicencio, Aline
%A Boitet, Christian
%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 ramisch-etal-2010-mwetoolkit
%X This paper presents the Multiword Expression Toolkit (mwetoolkit), an environment for type and language-independent MWE identification from corpora. The mwetoolkit provides a targeted list of MWE candidates, extracted and filtered according to a number of user-defined criteria and a set of standard statistical association measures. For generating corpus counts, the toolkit provides both a corpus indexation facility and a tool for integration with web search engines, while for evaluation, it provides validation and annotation facilities. The mwetoolkit also allows easy integration with a machine learning tool for the creation and application of supervised MWE extraction models if annotated data is available. In our experiment, the mwetoolkit was tested and evaluated in the context of MWE extraction in the biomedical domain. Our preliminary results show that the toolkit performs better than other approaches, especially concerning recall. Moreover, this first version can also be extended in several ways in order to improve the quality of the results.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/803_Paper.pdf
Markdown (Informal)
[mwetoolkit: a Framework for Multiword Expression Identification](http://www.lrec-conf.org/proceedings/lrec2010/pdf/803_Paper.pdf) (Ramisch et al., LREC 2010)
ACL