8485 articles  [version française]

inria-00088818, version 3

A Study on Learnability for Rigid Lambek Grammars

Roberto Bonato () a, 1, 2

N° RR-5964 (2006)

Abstract: We present basic notions of Gold's "learnability in the limit" paradigm, first presented in 1967, a formalization of the cognitive process by which a native speaker gets to grasp the underlying grammar of his/her own native language by being exposed to well formed sentences generated by that grammar. Then we present Lambek grammars, a formalism issued from categorial grammars which, although not as expressive as needed for a full formalization of natural languages, is particularly suited to easily implement a natural interface between syntax and semantics. In the last part of this work, we present a learnability result for Rigid Lambek grammars from structured examples.

  • a –  Université Sciences et Technologies - Bordeaux I
  • 1:  SIGNES (INRIA Futurs)
  • INRIA – CNRS : UMR5800 – Université Sciences et Technologies - Bordeaux I – Université Michel de Montaigne - Bordeaux III – École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)
  • 2:  Laboratoire Bordelais de Recherche en Informatique (LaBRI)
  • CNRS : UMR5800 – Université Sciences et Technologies - Bordeaux I – École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB) – Université Victor Segalen - Bordeaux II
  • Domain : Computer Science/Learning
  • Keywords : Formal Learning Theory – machine learning – Lambek calculus – computational linguistics – formal grammars
  • Internal note : RR-5964
  • Available versions :  v1 (2006-08-06) v2 (2006-08-07) v3 (2007-01-26)
 
  • inria-00088818, version 3
  • http://hal.inria.fr/inria-00088818
  • oai:hal.inria.fr:inria-00088818
  • From: Roberto Bonato <>
  • Submitted on: Friday, 26 January 2007 15:52:35
  • Updated on: Friday, 26 January 2007 16:17:12