Predicting globally-coherent temporal structures from texts via endpoint inference and graph decomposition

Abstract : An elegant approach to learning temporal order- ings from texts is to formulate this problem as a constraint optimization problem, which can be then given an exact solution using Integer Linear Programming. This works well for cases where the number of possible relations between temporal entities is restricted to the mere precedence rela- tion [Bramsen et al., 2006; Chambers and Jurafsky, 2008], but becomes impractical when considering all possible interval relations. This paper proposes two innovations, inspired from work on temporal reasoning, that control this combinatorial blow-up, therefore rendering an exact ILP inference viable in the general case. First, we translate our network of constraints from temporal intervals to their end- points, to handle a drastically smaller set of con- straints, while preserving the same temporal infor- mation. Second, we show that additional efficiency is gained by enforcing coherence on particular sub- sets of the entire temporal graphs. We evaluate these innovations through various experiments on TimeBank 1.2, and compare our ILP formulations with various baselines and oracle systems.
Type de document :
Communication dans un congrès
IJCAI-11 - International Joint Conference on Artificial Intelligence, Jul 2011, Barcelone, Spain. 2011
Liste complète des métadonnées

Littérature citée [8 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00614765
Contributeur : Pascal Denis <>
Soumis le : mardi 16 août 2011 - 11:48:13
Dernière modification le : vendredi 25 mai 2018 - 12:02:05
Document(s) archivé(s) le : vendredi 25 novembre 2011 - 11:12:33

Fichier

ijcai11.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00614765, version 1

Collections

Citation

Pascal Denis, Philippe Muller. Predicting globally-coherent temporal structures from texts via endpoint inference and graph decomposition. IJCAI-11 - International Joint Conference on Artificial Intelligence, Jul 2011, Barcelone, Spain. 2011. 〈inria-00614765〉

Partager

Métriques

Consultations de la notice

257

Téléchargements de fichiers

164