@inproceedings{agirre-etal-2010-exploring,
title = "Exploring Knowledge Bases for Similarity",
author = "Agirre, Eneko and
Cuadros, Montse and
Rigau, German and
Soroa, Aitor",
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/534_Paper.pdf",
abstract = "Graph-based similarity over WordNet has been previously shown to perform very well on word similarity. This paper presents a study of the performance of such a graph-based algorithm when using different relations and versions of Wordnet. The graph algorithm is based on Personalized PageRank, a random-walk based algorithm which computes the probability of a random-walk initiated in the target word to reach any synset following the relations in WordNet (Haveliwala, 2002). Similarity is computed as the cosine of the probability distributions for each word over WordNet. The best combination of relations includes all relations in WordNet 3.0, included disambiguated glosses, and automatically disambiguated topic signatures called KnowNets. All relations are part of the official release of WordNet, except KnowNets, which have been derived automatically. The results over the WordSim 353 dataset show that using the adequate relations the performance improves over previously published WordNet-based results on the WordSim353 dataset (Finkelstein et al., 2002). The similarity software and some graphs used in this paper are publicly available at \url{http://ixa2.si.ehu.es/ukb}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="agirre-etal-2010-exploring">
<titleInfo>
<title>Exploring Knowledge Bases for Similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eneko</namePart>
<namePart type="family">Agirre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Montse</namePart>
<namePart type="family">Cuadros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="family">Rigau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aitor</namePart>
<namePart type="family">Soroa</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>Graph-based similarity over WordNet has been previously shown to perform very well on word similarity. This paper presents a study of the performance of such a graph-based algorithm when using different relations and versions of Wordnet. The graph algorithm is based on Personalized PageRank, a random-walk based algorithm which computes the probability of a random-walk initiated in the target word to reach any synset following the relations in WordNet (Haveliwala, 2002). Similarity is computed as the cosine of the probability distributions for each word over WordNet. The best combination of relations includes all relations in WordNet 3.0, included disambiguated glosses, and automatically disambiguated topic signatures called KnowNets. All relations are part of the official release of WordNet, except KnowNets, which have been derived automatically. The results over the WordSim 353 dataset show that using the adequate relations the performance improves over previously published WordNet-based results on the WordSim353 dataset (Finkelstein et al., 2002). The similarity software and some graphs used in this paper are publicly available at http://ixa2.si.ehu.es/ukb.</abstract>
<identifier type="citekey">agirre-etal-2010-exploring</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/534_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Knowledge Bases for Similarity
%A Agirre, Eneko
%A Cuadros, Montse
%A Rigau, German
%A Soroa, Aitor
%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 agirre-etal-2010-exploring
%X Graph-based similarity over WordNet has been previously shown to perform very well on word similarity. This paper presents a study of the performance of such a graph-based algorithm when using different relations and versions of Wordnet. The graph algorithm is based on Personalized PageRank, a random-walk based algorithm which computes the probability of a random-walk initiated in the target word to reach any synset following the relations in WordNet (Haveliwala, 2002). Similarity is computed as the cosine of the probability distributions for each word over WordNet. The best combination of relations includes all relations in WordNet 3.0, included disambiguated glosses, and automatically disambiguated topic signatures called KnowNets. All relations are part of the official release of WordNet, except KnowNets, which have been derived automatically. The results over the WordSim 353 dataset show that using the adequate relations the performance improves over previously published WordNet-based results on the WordSim353 dataset (Finkelstein et al., 2002). The similarity software and some graphs used in this paper are publicly available at http://ixa2.si.ehu.es/ukb.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/534_Paper.pdf
Markdown (Informal)
[Exploring Knowledge Bases for Similarity](http://www.lrec-conf.org/proceedings/lrec2010/pdf/534_Paper.pdf) (Agirre et al., LREC 2010)
ACL
- Eneko Agirre, Montse Cuadros, German Rigau, and Aitor Soroa. 2010. Exploring Knowledge Bases for Similarity. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).