Textual Energy of Associative Memories: Performant Applications of Enertex Algorithm in Text Summarization and Topic Segmentation

Silvia Fernández (1, 2) , Eric Sanjuan (2) , Juan-Manuel Torres-Moreno (3, 2)

1 LPM - Laboratoire de physique des matériaux
2 LIA - Laboratoire Informatique d'Avignon
3 EPM - École Polytechnique de Montréal

In this paper we present a Neural Network approach, inspired by statistical physics of magnetic systems, to study fundamental problems of Natural Language Processing (NLP). The algorithm models documents as neural network whose Textual Energy is studied. We obtained good results on the application of this method to automatic summarization and Topic Segmentation.

Mots clés: Automatic Summarization; Topic Segmentation; Statistical Methods; Statistical Physics

Domaines: Informatique [cs]

Silvia Fernández, Eric Sanjuan, Juan-Manuel Torres-Moreno. Textual Energy of Associative Memories: Performant Applications of Enertex Algorithm in Text Summarization and Topic Segmentation. MICAI 2007 6th Mexican International Conference on Artificial Intelligence, Nov 2007, Aguascalientes, Mexico. ⟨10.1007/978-3-540-76631-5_82⟩. ⟨hal-01320291⟩