| Summary: | Submitted by Jos? Henrique Henrique (jose.neves@ufvjm.edu.br) on 2018-04-19T18:44:37Z
No. of bitstreams: 2
license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5)
luis_henrique_goncalves_aguiar.pdf: 1963486 bytes, checksum: ce8ee9274d520386492773d2e289f109 (MD5) === Approved for entry into archive by Rodrigo Martins Cruz (rodrigo.cruz@ufvjm.edu.br) on 2018-04-23T16:27:14Z (GMT) No. of bitstreams: 2
license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5)
luis_henrique_goncalves_aguiar.pdf: 1963486 bytes, checksum: ce8ee9274d520386492773d2e289f109 (MD5) === Made available in DSpace on 2018-04-23T16:27:14Z (GMT). No. of bitstreams: 2
license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5)
luis_henrique_goncalves_aguiar.pdf: 1963486 bytes, checksum: ce8ee9274d520386492773d2e289f109 (MD5)
Previous issue date: 2017 === Considerando a grande quantidade de informa??es textuais dispon?veis atualmente,
principalmente na web, est? se tronando cada vez mais dif?cil o acesso e a assimila??o desse
conte?do para o usu?rio. Nesse contexto, torna-se necess?rio buscar tarefas capazes de
transformar essa grande quantidade de dados em conhecimento ?til e organizado. Uma
alternativa para amenizar esse problema, ? reduzir o volume de informa??es dispon?veis a partir
da produ??o de resumos dos textos originais, por meio da sumariza??o autom?tica (SA) de
textos. A sumariza??o autom?tica de textos consiste na produ??o autom?tica de resumos a partir
de um ou mais textos-fonte, de modo que o sum?rio contenha as informa??es mais relevantes
deste. A avalia??o de resumos ? uma tarefa importante no campo da sumariza??o autom?tica
de texto, a abordagem mais intuitiva ? a avalia??o humana, por?m ? onerosa e improdutiva.
Outra alternativa ? a avalia??o autom?tica, alguns avaliadores foram propostos, sendo a mais
conhecida e amplamente usada ? a medida ROUGE (Recall-Oriented Understudy for Gisting
Evaluation). Um fator limitante na avalia??o da ROUGE ? a utiliza??o do sum?rio humano de
refer?ncia, o que implica em uma restri??o do idioma e dom?nio, al?m de requerer um trabalho
humano demorado e oneroso. Diante das dificuldades encontradas na avalia??o de sum?rios
autom?ticos, o presente trabalho apresenta o modelo Cassiopeia como um novo m?todo de
avalia??o. O modelo ? um agrupador de textos hier?rquico, o qual consiste no uso da
sumariza??o na etapa do pr?-processamento, onde a qualidade do agrupamento ? influenciada
positivamente conforme a qualidade da sumariza??o. As simula??es realizadas neste trabalho
mostraram que a avalia??o realizada pelo modelo Cassiopeia ? semelhante a avalia??o realizada
pela ferramenta ROUGE. Por outro lado, a utiliza??o do modelo Cassiopeia como avaliador de
sum?rios autom?ticos evidenciou algumas vantagens, sendo as principais; a n?o utiliza??o do
sum?rio humano no processo de avalia??o, e a independ?ncia do dom?nio e do idioma. === Disserta??o (Mestrado Profissional) ? Programa de P?s-Gradua??o em Educa??o, Universidade Federal dos Vales do Jequitinhonha e Mucuri, 2017. === Considering the large amount of textual information currently available, especially on the web,
it is becoming increasingly difficult to access and assimilate this content to the user. In this
context, it becomes necessary to search for tasks that can transform this large amount of
information into useful and organized knowledge. The solution, or at least an alternative, to
moderate this problem is to reduce the volume of information available, from the production of
abstracts of the original texts, through automatic summarization (SA) of texts. The Automatic
Summarization of texts consists of the automatic production of abstracts from one or more
source texts, which the summary must contain the most relevant information of the source text.
The evaluation of abstracts is an important task in the field of automatic text summarization,
the most intuitive approach is human evaluation, but it is costly and unproductive. Another
alternative is the automatic evaluation, some evaluators have been proposed, and the most
widely used is the ROUGE (Recall-Oriented Understudy for Gisting Evaluation). A limiting
factor in ROUGE's evaluation is the use of the human reference summary, which implies a
restriction of language and domain, as well as requiring time-consuming and expensive human
work. In view of the difficulties encountered in the evaluation of automatic summaries, this
paper presents the Cassiopeia model as a new evaluation method. The model is a hierarchical
text grouper, which consists of the use of the summarization in the stage of the pre-processing,
where the quality of the grouping is influenced positively according to the quality of the
summarization. The simulations performed in this work showed that the evaluations performed
by Cassiopeia in comparison to the ROUGE tool are similar. On the other hand, the use of the
Cassiopeia model as an automatic summarization evaluator showed some advantages, the main
ones are; being the non-use of the human abstract in the evaluation process, and the independent
of the domain and the language.
|
|---|
