Sumarização automática abstrativa de textos utilizando Deep Learning

• Main Author: Santos, Thiago Lourenço dos
• Publication Date: 2020
• Format: Bachelor thesis
• Language: por
• Source: Repositório Institucional da UFGD
• Download full: http://repositorio.ufgd.edu.br/jspui/handle/prefix/4649
• topic: Processamento de linguagem natural (Ciência da computação); Aprendizagem profunda; Sumarização abstrata; Natural language processing (Computer science); Deep Learning; Abstractive summarization; CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO

Deep learning has been used successfully in several applications in Natural Language Processing area. One of the applications is summarization of sentences, which can be extractive or abstractive. In this work, abstract summarization is addressed, on which summary is generated from abstractions and linguistic techniques, with the possibility of using words not found in the input sentence, which does not occur in extractive summarization, on which the output is a subset of the input. In this work, five papers were selected, in which the two most recent articles implementations were executed and tested, with the results being compared with those published in the articles and with the comparative analysis of some of the summaries generated by the trained models.