Learning Sequential Tree-to-Word Transducers - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Learning Sequential Tree-to-Word Transducers

Résumé

We study the problem of learning sequential top-down tree-to- word transducers (STWs). First, we present a Myhill-Nerode characterization of the corresponding class of sequential tree-to-word transformations (STW). Next, we investigate what learning of stws means, identify fundamental obstacles, and propose a learning model with abstain. Finally, we present a polynomial learning algorithm.

A long version is available here

Fichier principal
Vignette du fichier
main.pdf (209.25 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00912969 , version 1 (03-12-2013)

Identifiants

  • HAL Id : hal-00912969 , version 1

Citer

Grégoire Laurence, Aurélien Lemay, Joachim Niehren, Slawomir Staworko, Marc Tommasi. Learning Sequential Tree-to-Word Transducers. 8th International Conference on Language and Automata Theory and Applications, Mar 2014, Madrid, Spain. ⟨hal-00912969⟩
339 Consultations
213 Téléchargements

Partager

Gmail Facebook X LinkedIn More