Identification reversible dependency tree languages - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2001

Identification reversible dependency tree languages

Résumé

We investigate learning dependency grammar from positive data, in Gold's identification in the limit model. Examples are dependency trees. For this, we introduce reversible lexical dependency grammars which generate a significant class of languages. We have demonstrated that reversible dependency languages are learnable. We provide a $O(n^2)$-time, in the example size, algorithm.

Domaines

Autre [cs.OH]
Fichier non déposé

Dates et versions

inria-00100423 , version 1 (26-09-2006)

Identifiants

  • HAL Id : inria-00100423 , version 1

Citer

Jérôme Besombes, Jean-Yves Marion. Identification reversible dependency tree languages. 3rd Learning Language in Logic (LLL) Workshop, L. Popelinsky, M. Nepil, Sep 2001, Strasbourg, France, 12 p. ⟨inria-00100423⟩
76 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More