Generative event schema induction with entity disambiguation

K.-H. Nguyen (1, 2) , X. Tannier (2) , Olivier Ferret (1) , R. Besancon (1)

1 DIASI (CEA, LIST) - Département Intelligence Ambiante et Systèmes Interactifs
2 LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur

This paper presents a generative model to event schema induction. Previous methods in the literature only use head words to represent entities. However, elements other than head words contain useful information. For instance, an armed man is more discriminative than man. Our model takes into account this information and precisely represents it using probabilistic topic distributions. We illustrate that such information plays an important role in parameter estimation. Mostly, it makes topic distributions more coherent and more discriminative. Experimental results on benchmark dataset empirically confirm this enhancement.

Mots clés: Computational linguistics; Information use; Linguistics; Probability distributions; Benchmark datasets; Entity disambiguation; Generative model; Topic distributions; Natural language processing systems

Domaines: Physique [physics]

K.-H. Nguyen, X. Tannier, Olivier Ferret, R. Besancon. Generative event schema induction with entity disambiguation. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, Jul 2015, Beijing, China. pp.188-197. ⟨cea-01844047⟩