Comparison of different algebras for inducing the temporal structure of texts

Abstract : This paper investigates the impact of using different temporal algebras for learning temporal relations between events. Specifically, we compare three interval-based algebras: Allen \shortcite{Allen83} algebra, Bruce \shortcite{Bruce72} algebra, and the algebra derived from the TempEval-07 campaign. These algebras encode different granularities of relations and have different inferential properties. They in turn behave differently when used to enforce global consistency constraints on the building of a temporal representation. Through various experiments on the TimeBank/AQUAINT corpus, we show that although the TempEval relation set leads to the best classification accuracy performance, it is too vague to be used for enforcing consistency. By contrast, the other two relation sets are similarly harder to learn, but more useful when global consistency is important. Overall, the Bruce algebra is shown to give the best compromise between learnability and expressive power.
Type de document :
Communication dans un congrès
Coling 2010 Organizing Committee. Proceedings of the 23rd International Conference on Computational Linguistics - Coling 2010, Aug 2010, Beijing, China. pp.250--258, 2010, 〈http://www.aclweb.org/anthology/C10-1029.pdf〉
Liste complète des métadonnées

https://hal.inria.fr/inria-00511586
Contributeur : Philippe Muller <>
Soumis le : mercredi 25 août 2010 - 14:42:01
Dernière modification le : jeudi 15 novembre 2018 - 20:27:26

Identifiants

  • HAL Id : inria-00511586, version 1

Collections

Citation

Pascal Denis, Philippe Muller. Comparison of different algebras for inducing the temporal structure of texts. Coling 2010 Organizing Committee. Proceedings of the 23rd International Conference on Computational Linguistics - Coling 2010, Aug 2010, Beijing, China. pp.250--258, 2010, 〈http://www.aclweb.org/anthology/C10-1029.pdf〉. 〈inria-00511586〉

Partager

Métriques

Consultations de la notice

215