@inproceedings{shinnou-sasaki-2008-spectral,
title = "Spectral Clustering for a Large Data Set by Reducing the Similarity Matrix Size",
author = "Shinnou, Hiroyuki and
Sasaki, Minoru",
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/62_paper.pdf",
abstract = "Spectral clustering is a powerful clustering method for document data set. However, spectral clustering needs to solve an eigenvalue problem of the matrix converted from the similarity matrix corresponding to the data set. Therefore, it is not practical to use spectral clustering for a large data set. To overcome this problem, we propose the method to reduce the similarity matrix size. First, using k-means, we obtain a clustering result for the given data set. From each cluster, we pick up some data, which are near to the central of the cluster. We take these data as one data. We call this data set as committee. Data except for committees remain one data. For these data, we construct the similarity matrix. Definitely, the size of this similarity matrix is reduced so much that we can perform spectral clustering using the reduced similarity matrix.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shinnou-sasaki-2008-spectral">
<titleInfo>
<title>Spectral Clustering for a Large Data Set by Reducing the Similarity Matrix Size</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hiroyuki</namePart>
<namePart type="family">Shinnou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minoru</namePart>
<namePart type="family">Sasaki</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>Spectral clustering is a powerful clustering method for document data set. However, spectral clustering needs to solve an eigenvalue problem of the matrix converted from the similarity matrix corresponding to the data set. Therefore, it is not practical to use spectral clustering for a large data set. To overcome this problem, we propose the method to reduce the similarity matrix size. First, using k-means, we obtain a clustering result for the given data set. From each cluster, we pick up some data, which are near to the central of the cluster. We take these data as one data. We call this data set as committee. Data except for committees remain one data. For these data, we construct the similarity matrix. Definitely, the size of this similarity matrix is reduced so much that we can perform spectral clustering using the reduced similarity matrix.</abstract>
<identifier type="citekey">shinnou-sasaki-2008-spectral</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/62_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Spectral Clustering for a Large Data Set by Reducing the Similarity Matrix Size
%A Shinnou, Hiroyuki
%A Sasaki, Minoru
%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 shinnou-sasaki-2008-spectral
%X Spectral clustering is a powerful clustering method for document data set. However, spectral clustering needs to solve an eigenvalue problem of the matrix converted from the similarity matrix corresponding to the data set. Therefore, it is not practical to use spectral clustering for a large data set. To overcome this problem, we propose the method to reduce the similarity matrix size. First, using k-means, we obtain a clustering result for the given data set. From each cluster, we pick up some data, which are near to the central of the cluster. We take these data as one data. We call this data set as committee. Data except for committees remain one data. For these data, we construct the similarity matrix. Definitely, the size of this similarity matrix is reduced so much that we can perform spectral clustering using the reduced similarity matrix.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/62_paper.pdf
Markdown (Informal)
[Spectral Clustering for a Large Data Set by Reducing the Similarity Matrix Size](http://www.lrec-conf.org/proceedings/lrec2008/pdf/62_paper.pdf) (Shinnou & Sasaki, LREC 2008)
ACL