@inproceedings{azeredo-etal-2008-keywords,
title = "Keywords, k-{NN} and Neural Networks: a Support for Hierarchical Categorization of Texts in {B}razilian {P}ortuguese",
author = "Azeredo, Susana and
Moraes, Silvia and
Lima, Vera",
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/402_paper.pdf",
abstract = "A frequent problem in automatic categorization applications involving Portuguese language is the absence of large corpora of previously classified documents, which permit the validation of experiments carried out. Generally, the available corpora are not classified or, when they are, they contain a very reduced number of documents. The general goal of this study is to contribute to the development of applications which aim at text categorization for Brazilian Portuguese. Specifically, we point out that keywords selection associated with neural networks can improve results in the categorization of Brazilian Portuguese texts. The corpus is composed of 30 thousand texts from the Folha de S{\~a}o Paulo newspaper, organized in 29 sections. In the process of categorization, the k-Nearest Neighbor (k-NN) algorithm and the Multilayer Perceptron neural networks trained with the backpropagation algorithm are used. It is also part of our study to test the identification of keywords parting from the log-likelihood statistical measure and to use them as features in the categorization process. The results clearly show that the precision is better when using neural networks than when using the k-NN.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="azeredo-etal-2008-keywords">
<titleInfo>
<title>Keywords, k-NN and Neural Networks: a Support for Hierarchical Categorization of Texts in Brazilian Portuguese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Susana</namePart>
<namePart type="family">Azeredo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Silvia</namePart>
<namePart type="family">Moraes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Lima</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>A frequent problem in automatic categorization applications involving Portuguese language is the absence of large corpora of previously classified documents, which permit the validation of experiments carried out. Generally, the available corpora are not classified or, when they are, they contain a very reduced number of documents. The general goal of this study is to contribute to the development of applications which aim at text categorization for Brazilian Portuguese. Specifically, we point out that keywords selection associated with neural networks can improve results in the categorization of Brazilian Portuguese texts. The corpus is composed of 30 thousand texts from the Folha de São Paulo newspaper, organized in 29 sections. In the process of categorization, the k-Nearest Neighbor (k-NN) algorithm and the Multilayer Perceptron neural networks trained with the backpropagation algorithm are used. It is also part of our study to test the identification of keywords parting from the log-likelihood statistical measure and to use them as features in the categorization process. The results clearly show that the precision is better when using neural networks than when using the k-NN.</abstract>
<identifier type="citekey">azeredo-etal-2008-keywords</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/402_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Keywords, k-NN and Neural Networks: a Support for Hierarchical Categorization of Texts in Brazilian Portuguese
%A Azeredo, Susana
%A Moraes, Silvia
%A Lima, Vera
%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 azeredo-etal-2008-keywords
%X A frequent problem in automatic categorization applications involving Portuguese language is the absence of large corpora of previously classified documents, which permit the validation of experiments carried out. Generally, the available corpora are not classified or, when they are, they contain a very reduced number of documents. The general goal of this study is to contribute to the development of applications which aim at text categorization for Brazilian Portuguese. Specifically, we point out that keywords selection associated with neural networks can improve results in the categorization of Brazilian Portuguese texts. The corpus is composed of 30 thousand texts from the Folha de São Paulo newspaper, organized in 29 sections. In the process of categorization, the k-Nearest Neighbor (k-NN) algorithm and the Multilayer Perceptron neural networks trained with the backpropagation algorithm are used. It is also part of our study to test the identification of keywords parting from the log-likelihood statistical measure and to use them as features in the categorization process. The results clearly show that the precision is better when using neural networks than when using the k-NN.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/402_paper.pdf
Markdown (Informal)
[Keywords, k-NN and Neural Networks: a Support for Hierarchical Categorization of Texts in Brazilian Portuguese](http://www.lrec-conf.org/proceedings/lrec2008/pdf/402_paper.pdf) (Azeredo et al., LREC 2008)
ACL