@inproceedings{etcheverry-wonsever-2016-spanish,
title = "{S}panish Word Vectors from {W}ikipedia",
author = "Etcheverry, Mathias and
Wonsever, Dina",
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/L16-1584",
pages = "3681--3685",
abstract = "Contents analisys from text data requires semantic representations that are difficult to obtain automatically, as they may require large handcrafted knowledge bases or manually annotated examples. Unsupervised autonomous methods for generating semantic representations are of greatest interest in face of huge volumes of text to be exploited in all kinds of applications. In this work we describe the generation and validation of semantic representations in the vector space paradigm for Spanish. The method used is GloVe (Pennington, 2014), one of the best performing reported methods , and vectors were trained over Spanish Wikipedia. The learned vectors evaluation is done in terms of word analogy and similarity tasks (Pennington, 2014; Baroni, 2014; Mikolov, 2013a). The vector set and a Spanish version for some widely used semantic relatedness tests are made publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="etcheverry-wonsever-2016-spanish">
<titleInfo>
<title>Spanish Word Vectors from Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mathias</namePart>
<namePart type="family">Etcheverry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Wonsever</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>Contents analisys from text data requires semantic representations that are difficult to obtain automatically, as they may require large handcrafted knowledge bases or manually annotated examples. Unsupervised autonomous methods for generating semantic representations are of greatest interest in face of huge volumes of text to be exploited in all kinds of applications. In this work we describe the generation and validation of semantic representations in the vector space paradigm for Spanish. The method used is GloVe (Pennington, 2014), one of the best performing reported methods , and vectors were trained over Spanish Wikipedia. The learned vectors evaluation is done in terms of word analogy and similarity tasks (Pennington, 2014; Baroni, 2014; Mikolov, 2013a). The vector set and a Spanish version for some widely used semantic relatedness tests are made publicly available.</abstract>
<identifier type="citekey">etcheverry-wonsever-2016-spanish</identifier>
<location>
<url>https://aclanthology.org/L16-1584</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3681</start>
<end>3685</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Spanish Word Vectors from Wikipedia
%A Etcheverry, Mathias
%A Wonsever, Dina
%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 etcheverry-wonsever-2016-spanish
%X Contents analisys from text data requires semantic representations that are difficult to obtain automatically, as they may require large handcrafted knowledge bases or manually annotated examples. Unsupervised autonomous methods for generating semantic representations are of greatest interest in face of huge volumes of text to be exploited in all kinds of applications. In this work we describe the generation and validation of semantic representations in the vector space paradigm for Spanish. The method used is GloVe (Pennington, 2014), one of the best performing reported methods , and vectors were trained over Spanish Wikipedia. The learned vectors evaluation is done in terms of word analogy and similarity tasks (Pennington, 2014; Baroni, 2014; Mikolov, 2013a). The vector set and a Spanish version for some widely used semantic relatedness tests are made publicly available.
%U https://aclanthology.org/L16-1584
%P 3681-3685
Markdown (Informal)
[Spanish Word Vectors from Wikipedia](https://aclanthology.org/L16-1584) (Etcheverry & Wonsever, LREC 2016)
ACL
- Mathias Etcheverry and Dina Wonsever. 2016. Spanish Word Vectors from Wikipedia. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 3681–3685, Portorož, Slovenia. European Language Resources Association (ELRA).