Work

An Evolutionary Algorithm for Automatic Summarization

Year: 2017

Type: conference-paper

Abstract: This paper proposes a novel method to select sentences for automatic summarization based on an evolutionary algorithm.The algorithm explores candidate summaries space following an objective function computed over ngrams probability distributions of the candidate summary and the source documents.This method does not consider a summary as a stack of independent sentences but as a whole text, and makes use of advances in unsupervised summarization evaluation.We compare this sentence extraction method to one of the best existing methods which is based on integer linear programming, and show its efficiency on three different acknowledged corpora.

Source: International conference Recent advances in natural language processing

DOI: 10.26615/978-954-452-049-6_017

Authors: LIASD - EA 4383, Université Paris 8, Saint-Denis, France, Aurélien Bossard, Christophe Rodrigues

Institutions: Pôle Léonard de Vinci, Université Paris 8

Language: English

Topic: Advanced Text Analysis Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

Funder: Agence Nationale de la Recherche

Award: Automatic Summarization for All-Digital ERA