Un r\'esumeur \`a base de graphes, ind\'ep\'endant de la langue

TL;DR

This paper introduces REG, a language-independent graph-based algorithm for automatic text summarization that models documents as graphs and computes sentence weights, successfully applied across three languages.

Contribution

The paper presents a novel language-independent graph-based method for automatic text summarization, capable of handling multiple languages.

Findings

Effective across three languages

Successfully computes sentence importance

Provides a language-independent summarization approach

Abstract

In this paper we present REG, a graph-based approach for study a fundamental problem of Natural Language Processing (NLP): the automatic text summarization. The algorithm maps a document as a graph, then it computes the weight of their sentences. We have applied this approach to summarize documents in three languages.