Textual entailment by generality - Mines Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

Textual entailment by generality

Gaël Dias
Katarzyna Wegrzyn-Wolska
Pierre Jouvelot

Résumé

Textual Entailment consists in determining if an entailment relation exists between two texts. In this paper, we present an Informative Asymmetric Measure called the Asymmetric InfoSimba (AIS), which we combine with different asym-metric association measures to recognize the specific case of Textual Entailment by Generality. In particular, the AIS proposes an unsupervised, language-independent, threshold free solution. This new measure is tested against the first Recognizing Textual Entailment dataset for an exhaustive number of asymmetric association measures and shows that the combination of the AIS with the Braun-Blanket steadily improves results against competitive measures such as the one proposed by [1].
Fichier principal
Vignette du fichier
CHS-DIAS-2011-1.pdf (8.12 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-00659339 , version 1 (03-10-2014)

Identifiants

Citer

Sebastiao Pais, Gaël Dias, Katarzyna Wegrzyn-Wolska, Robert Mahl, Pierre Jouvelot. Textual entailment by generality. Conference on Pacific Association for Computational Lingustics, PACLING 2011, Jul 2011, Kuala Lumpur, Malaysia. pp.258-266, ⟨10.1016/j.sbspro.2011.10.606⟩. ⟨hal-00659339⟩
271 Consultations
181 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More