Utiliza\c{c}\~ao de Grafos e Matriz de Similaridade na Sumariza\c{c}\~ao Autom\'atica de Documentos Baseada em Extra\c{c}\~ao de Frases

TL;DR

This paper presents a method for automatic text summarization using graph-based heuristics and similarity matrices, evaluated across multiple languages and corpora with promising results.

Contribution

It introduces a novel approach combining graph techniques and similarity matrices for sentence extraction in automatic summarization.

Findings

Effective summarization across English, French, and Spanish.

Promising results demonstrated on multiple language corpora.

Method enhances relevance measurement for sentence extraction.

Abstract

The internet increased the amount of information available. However, the reading and understanding of this information are costly tasks. In this scenario, the Natural Language Processing (NLP) applications enable very important solutions, highlighting the Automatic Text Summarization (ATS), which produce a summary from one or more source texts. Automatically summarizing one or more texts, however, is a complex task because of the difficulties inherent to the analysis and generation of this summary. This master's thesis describes the main techniques and methodologies (NLP and heuristics) to generate summaries. We have also addressed and proposed some heuristics based on graphs and similarity matrix to measure the relevance of judgments and to generate summaries by extracting sentences. We used the multiple languages (English, French and Spanish), CSTNews (Brazilian Portuguese), RPM (French) and DECODA (French) corpus to evaluate the developped systems. The results obtained were quite interesting.