Discarding Impossible Events from Statistical Language Models - Inria - Institut national de recherche en sciences et technologies du numérique
Communication Dans Un Congrès Année : 2000

Discarding Impossible Events from Statistical Language Models

Résumé

This paper describes a method for detectingvimpossible bigrams using a vocabulary of V elements. The idea is to discard all the ungrammatical events to expect an improvement of the language model. We extract the impossible bigrams by using automatic rules. The biclass associations which are ungrammatical are detected and all the corresponding bigrams are analyzed and set as possible or impossible events, we also decided to manage for each of the retrieved rule an exception list.
Fichier principal
Vignette du fichier
A00-R-221.pdf (69.78 Ko) Télécharger le fichier
Loading...

Dates et versions

inria-00099040 , version 1 (26-09-2006)

Identifiants

  • HAL Id : inria-00099040 , version 1

Citer

Armelle Brun, David Langlois, Kamel Smaïli, Jean-Paul Haton. Discarding Impossible Events from Statistical Language Models. International Conference on Spoken Language Processing, Oct 2000, Pékin, China, 4 p. ⟨inria-00099040⟩
126 Consultations
88 Téléchargements

Partager

More