@inproceedings{peirsman-etal-2008-construction,
title = "The Construction and Evaluation of Word Space Models",
author = "Peirsman, Yves and
De Deyne, Simon and
Heylen, Kris and
Geeraerts, 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 = "https://aclanthology.org/L08-1168/",
abstract = "Semantic similarity is a key issue in many computational tasks. This paper goes into the development and evaluation of two common ways of automatically calculating the semantic similarity between two words. On the one hand, such methods may depend on a manually constructed thesaurus like (Euro)WordNet. Their performance is often evaluated on the basis of a very restricted set of human similarity ratings. On the other hand, corpus-based methods rely on the distribution of two words in a corpus to determine their similarity. Their performance is generally quantified through a comparison with the judgements of the first type of approach. This paper introduces a new Gold Standard of more than 5,000 human intra-category similarity judgements. We show that corpus-based methods often outperform (Euro)WordNet on this data set, and that the use of the latter as a Gold Standard for the former, is thus often far from ideal."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="peirsman-etal-2008-construction">
<titleInfo>
<title>The Construction and Evaluation of Word Space Models</title>
</titleInfo>
<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">Simon</namePart>
<namePart type="family">De Deyne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Dirk</namePart>
<namePart type="family">Geeraerts</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>Semantic similarity is a key issue in many computational tasks. This paper goes into the development and evaluation of two common ways of automatically calculating the semantic similarity between two words. On the one hand, such methods may depend on a manually constructed thesaurus like (Euro)WordNet. Their performance is often evaluated on the basis of a very restricted set of human similarity ratings. On the other hand, corpus-based methods rely on the distribution of two words in a corpus to determine their similarity. Their performance is generally quantified through a comparison with the judgements of the first type of approach. This paper introduces a new Gold Standard of more than 5,000 human intra-category similarity judgements. We show that corpus-based methods often outperform (Euro)WordNet on this data set, and that the use of the latter as a Gold Standard for the former, is thus often far from ideal.</abstract>
<identifier type="citekey">peirsman-etal-2008-construction</identifier>
<location>
<url>https://aclanthology.org/L08-1168/</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Construction and Evaluation of Word Space Models
%A Peirsman, Yves
%A De Deyne, Simon
%A Heylen, Kris
%A Geeraerts, 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 peirsman-etal-2008-construction
%X Semantic similarity is a key issue in many computational tasks. This paper goes into the development and evaluation of two common ways of automatically calculating the semantic similarity between two words. On the one hand, such methods may depend on a manually constructed thesaurus like (Euro)WordNet. Their performance is often evaluated on the basis of a very restricted set of human similarity ratings. On the other hand, corpus-based methods rely on the distribution of two words in a corpus to determine their similarity. Their performance is generally quantified through a comparison with the judgements of the first type of approach. This paper introduces a new Gold Standard of more than 5,000 human intra-category similarity judgements. We show that corpus-based methods often outperform (Euro)WordNet on this data set, and that the use of the latter as a Gold Standard for the former, is thus often far from ideal.
%U https://aclanthology.org/L08-1168/
Markdown (Informal)
[The Construction and Evaluation of Word Space Models](https://aclanthology.org/L08-1168/) (Peirsman et al., LREC 2008)
ACL
- Yves Peirsman, Simon De Deyne, Kris Heylen, and Dirk Geeraerts. 2008. The Construction and Evaluation of Word Space Models. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).