@inproceedings{heylen-etal-2008-modelling,
title = "Modelling Word Similarity: an Evaluation of Automatic Synonymy Extraction Algorithms.",
author = "Heylen, Kris and
Peirsman, Yves and
Geeraerts, Dirk and
Speelman, Dirk",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/818_paper.pdf",
abstract = "Vector-based models of lexical semantics retrieve semantically related words automatically from large corpora by exploiting the property that words with a similar meaning tend to occur in similar contexts. Despite their increasing popularity, it is unclear which kind of semantic similarity they actually capture and for which kind of words. In this paper, we use three vector-based models to retrieve semantically related words for a set of Dutch nouns and we analyse whether three linguistic properties of the nouns influence the results. In particular, we compare results from a dependency-based model with those from a 1st and 2nd order bag-of-words model and we examine the effect of the nouns frequency, semantic speficity and semantic class. We find that all three models find more synonyms for high-frequency nouns and those belonging to abstract semantic classses. Semantic specificty does not have a clear influence.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="heylen-etal-2008-modelling">
<titleInfo>
<title>Modelling Word Similarity: an Evaluation of Automatic Synonymy Extraction Algorithms.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kris</namePart>
<namePart type="family">Heylen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Peirsman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Geeraerts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Speelman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Vector-based models of lexical semantics retrieve semantically related words automatically from large corpora by exploiting the property that words with a similar meaning tend to occur in similar contexts. Despite their increasing popularity, it is unclear which kind of semantic similarity they actually capture and for which kind of words. In this paper, we use three vector-based models to retrieve semantically related words for a set of Dutch nouns and we analyse whether three linguistic properties of the nouns influence the results. In particular, we compare results from a dependency-based model with those from a 1st and 2nd order bag-of-words model and we examine the effect of the nouns frequency, semantic speficity and semantic class. We find that all three models find more synonyms for high-frequency nouns and those belonging to abstract semantic classses. Semantic specificty does not have a clear influence.</abstract>
<identifier type="citekey">heylen-etal-2008-modelling</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/818_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modelling Word Similarity: an Evaluation of Automatic Synonymy Extraction Algorithms.
%A Heylen, Kris
%A Peirsman, Yves
%A Geeraerts, Dirk
%A Speelman, Dirk
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F heylen-etal-2008-modelling
%X Vector-based models of lexical semantics retrieve semantically related words automatically from large corpora by exploiting the property that words with a similar meaning tend to occur in similar contexts. Despite their increasing popularity, it is unclear which kind of semantic similarity they actually capture and for which kind of words. In this paper, we use three vector-based models to retrieve semantically related words for a set of Dutch nouns and we analyse whether three linguistic properties of the nouns influence the results. In particular, we compare results from a dependency-based model with those from a 1st and 2nd order bag-of-words model and we examine the effect of the nouns frequency, semantic speficity and semantic class. We find that all three models find more synonyms for high-frequency nouns and those belonging to abstract semantic classses. Semantic specificty does not have a clear influence.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/818_paper.pdf
Markdown (Informal)
[Modelling Word Similarity: an Evaluation of Automatic Synonymy Extraction Algorithms.](http://www.lrec-conf.org/proceedings/lrec2008/pdf/818_paper.pdf) (Heylen et al., LREC 2008)
ACL