@inproceedings{cordeiro-etal-2016-mwetoolkit,
title = "mwetoolkit+sem: Integrating Word Embeddings in the mwetoolkit for Semantic {MWE} Processing",
author = "Cordeiro, Silvio and
Ramisch, Carlos and
Villavicencio, Aline",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1194",
pages = "1221--1225",
abstract = "This paper presents mwetoolkit+sem: an extension of the mwetoolkit that estimates semantic compositionality scores for multiword expressions (MWEs) based on word embeddings. First, we describe our implementation of vector-space operations working on distributional vectors. The compositionality score is based on the cosine distance between the MWE vector and the composition of the vectors of its member words. Our generic system can handle several types of word embeddings and MWE lists, and may combine individual word representations using several composition techniques. We evaluate our implementation on a dataset of 1042 English noun compounds, comparing different configurations of the underlying word embeddings and word-composition models. We show that our vector-based scores model non-compositionality better than standard association measures such as log-likelihood.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cordeiro-etal-2016-mwetoolkit">
<titleInfo>
<title>mwetoolkit+sem: Integrating Word Embeddings in the mwetoolkit for Semantic MWE Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Silvio</namePart>
<namePart type="family">Cordeiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</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>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents mwetoolkit+sem: an extension of the mwetoolkit that estimates semantic compositionality scores for multiword expressions (MWEs) based on word embeddings. First, we describe our implementation of vector-space operations working on distributional vectors. The compositionality score is based on the cosine distance between the MWE vector and the composition of the vectors of its member words. Our generic system can handle several types of word embeddings and MWE lists, and may combine individual word representations using several composition techniques. We evaluate our implementation on a dataset of 1042 English noun compounds, comparing different configurations of the underlying word embeddings and word-composition models. We show that our vector-based scores model non-compositionality better than standard association measures such as log-likelihood.</abstract>
<identifier type="citekey">cordeiro-etal-2016-mwetoolkit</identifier>
<location>
<url>https://aclanthology.org/L16-1194</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1221</start>
<end>1225</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T mwetoolkit+sem: Integrating Word Embeddings in the mwetoolkit for Semantic MWE Processing
%A Cordeiro, Silvio
%A Ramisch, Carlos
%A Villavicencio, Aline
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F cordeiro-etal-2016-mwetoolkit
%X This paper presents mwetoolkit+sem: an extension of the mwetoolkit that estimates semantic compositionality scores for multiword expressions (MWEs) based on word embeddings. First, we describe our implementation of vector-space operations working on distributional vectors. The compositionality score is based on the cosine distance between the MWE vector and the composition of the vectors of its member words. Our generic system can handle several types of word embeddings and MWE lists, and may combine individual word representations using several composition techniques. We evaluate our implementation on a dataset of 1042 English noun compounds, comparing different configurations of the underlying word embeddings and word-composition models. We show that our vector-based scores model non-compositionality better than standard association measures such as log-likelihood.
%U https://aclanthology.org/L16-1194
%P 1221-1225
Markdown (Informal)
[mwetoolkit+sem: Integrating Word Embeddings in the mwetoolkit for Semantic MWE Processing](https://aclanthology.org/L16-1194) (Cordeiro et al., LREC 2016)
ACL