Sentence Compression as a Step in Summarization or an Alternative Path in Text Shortening

Abstract : The originality of this work leads in tackling text compression using an unsupervised method, based on a deep linguistic analysis, and without resorting on a learning corpus. This work presents a system for dependent tree pruning, while preserving the syntactic coherence and the main informational contents, and led to an operational software, named COLIN. Experiment results show that our compressions get honorable satisfaction levels, with a mean compression ratio of 38 %.
Type de document :
Communication dans un congrès
Coling 2008 Organizing Committee. Coling'08: International Conference on Computational Linguistics, Aug 2008, Manchester, UK, pp.137-140, 2008, 〈http://www.coling2008.org.uk/〉
Liste complète des métadonnées

https://hal-lirmm.ccsd.cnrs.fr/lirmm-00318727
Contributeur : Mehdi Yousfi-Monod <>
Soumis le : jeudi 4 septembre 2008 - 17:36:47
Dernière modification le : jeudi 24 mai 2018 - 15:59:23
Document(s) archivé(s) le : lundi 8 octobre 2012 - 12:55:53

Identifiants

  • HAL Id : lirmm-00318727, version 1

Collections

Citation

Mehdi Yousfi-Monod, Violaine Prince. Sentence Compression as a Step in Summarization or an Alternative Path in Text Shortening. Coling 2008 Organizing Committee. Coling'08: International Conference on Computational Linguistics, Aug 2008, Manchester, UK, pp.137-140, 2008, 〈http://www.coling2008.org.uk/〉. 〈lirmm-00318727〉

Partager

Métriques

Consultations de la notice

284

Téléchargements de fichiers

284