Integrating Document Structure into a Multi-Document Summarizer
Résumé
In this paper, we present a novel approach for automatic summarization. CBSEAS, the system implementing this approach, integrates a method to detect redundancy at its very core, in order to produce more expressive summaries than previous approaches. The evaluation of our system during TAC 2008 |the Text Analysis Conference| revealed that, even if our system performed well on blogs, it had some failings on news stories. A post-mortem analysis of the weaknesses of our original system showed the importance of text structure for automatic summarization, even in the case of short texts like news stories. We describe some ongoing work dealing with these issues and show that first experiments provide a significant improvement of the results.
Origine : Fichiers produits par l'(les) auteur(s)
Loading...