Redes neurais recorrentes para a classificação de estruturas retóricas

Detalhes bibliográficos
Ano de defesa: 2018
Autor(a) principal: Moura, Gustavo Bennemann de
Orientador(a): Não Informado pela instituição
Banca de defesa: Não Informado pela instituição
Tipo de documento: Dissertação
Tipo de acesso: Acesso aberto
Idioma: por
Instituição de defesa: Universidade Estadual de Maringá.
Brasil
Departamento de Informática
Programa de Pós-Graduação em Ciência da Computação
Maringá, PR
Centro de Tecnologia
Programa de Pós-Graduação: Não Informado pela instituição
Departamento: Não Informado pela instituição
País: Não Informado pela instituição
Palavras-chave em Português:
Link de acesso: http://repositorio.uem.br:8080/jspui/handle/1/4601
Resumo: Rhetoric is the art of using language effectively and persuasively. One important factor about rhetoric is its structure, i.e. the organization of how such arguments are presented in the text. This Master?s work intend to evaluate if recurrent neural networks are able to contribute in the classification of rhetorical structure. To do this, it was necessary first to create a corpus with a large number of abstracts of scientific articles with their rhetorical structures annotated so that it was possible to train the proposed neural network architecture. The proposed recurrent neural network (RNN) uses LSTM (Long Short-Term Memory) layers to avoid the problems that are common in RNNs (vanishing and exploding gradients). An encoder-decoder layer was also used to obtain intermediate representations of the abstracts sentences so that it was possible to transform the word sequence into the abstract sentence into a fixed-length vector representing that sequence. For comparison, two baselines were implemented using the CRF and SVM machine learning algorithms, and with features that were used in other works in the literature. The results obtained by the proposed neural network were satisfactory. When comparing the best results of the network with the best results of the baselines, it was possible to observe 3.18% gain in the accuracy of the classification of rhetorical structures in abstracts as a whole. In the sentence classification, gains of 1.02% in accuracy and 0.88