Combining a Multi-document Summarization System with a Genetic Algorithm

Aurélien Bossard (1) , Christophe Rodrigues (1)

1 LIPN - Laboratoire d'Informatique de Paris-Nord

In this paper, we present a combination of a multi-document summarization system with a genetic algorithm. We first introduce a novel approach for automatic summarization. CBSEAS, the system which implements this approach, integrates a new method to detect redundancy at its very core in order to produce summaries with a good informational diversity. However, the evaluation of our system at TAC 2008 --Text Analysis Conference-- revealed that system adaptation to a specific domain is fundamental to obtain summaries of an acceptable quality. The second part of this paper is dedicated to a genetic algorithm which aims to adapt our system to specific domains. We present its evaluation by TAC 2009 on a newswire articles summarization task and show that this optimization is having a great influence on both human and automatic evaluations.

Mots clés: résumé automatique; algorithme génétique; optimisation

Domaines: Traitement du texte et du document; Apprentissage [cs.LG]

Aurélien Bossard, Christophe Rodrigues. Combining a Multi-document Summarization System with a Genetic Algorithm. CIMA 2010 - International Workshop on Combinations of Intelligend Methods and Applications,, Oct 2010, Arras, France, France. pp.71-87. ⟨hal-00573580⟩