HAL : hal-00186889, version 1

Fiche détaillée

Récupérer au format BibTeX - EndNote - TEI - RefWorks -

Journal of Machine Learning Research 8 (2007) 1725--1745

Polynomial Identification in the limit of context-free substitutable languages

A. Clark 1, Rémi Eyraud 2

Alexander Clark Collaboration(s)

(01/09/2007)

This paper formalises the idea of substitutability introduced by Zellig Harris in the 1950s and makes it the basis for a learning algorithm from positive data only for a subclass of context-free languages. We show that there is a polynomial characteristic set, and thus prove polynomial identification in the limit of this class. We discuss the relationship of this class of languages to other common classes discussed in grammatical inference. It transpires that it is not necessary to identify constituents in order to learn a context-free language -- it is sufficient to identify the syntactic congruence, and the operations of the syntactic monoid can be converted into a context-free grammar. We also discuss modifications to the algorithm that produces a reduction system rather than a context-free grammar, that will be much more compact. We discuss the relationship to Angluin's notion of reversibility for regular languages. We also demonstrate that an implementation of this algorithm is capable of learning a classic example of structure dependent syntax in English: this constitutes a refutation of an argument that has been used in support of nativist theories of language.

1 :	Department of Computer Science
	Royal Holloway, University of London
2 :	Laboratoire d'informatique Fondamentale de Marseille (LIF)
	CNRS : UMR6166 – Université de la Méditerranée - Aix-Marseille II – Université de Provence - Aix-Marseille I

Domaine

:

Informatique/Apprentissage Informatique/Traitement du texte et du document

Mots Clés : grammar induction – context-free languages – string rewritting systems – natural languages

hal-00186889, version 1

http://hal.archives-ouvertes.fr/hal-00186889

oai:hal.archives-ouvertes.fr:hal-00186889

Contributeur : Rémi Eyraud <>

Soumis le : Mercredi 14 Novembre 2007, 10:38:42

Dernière modification le : Mercredi 14 Novembre 2007, 17:19:50