Efficient linear combination for distant n-gram models

David Langlois 1 Kamel Smaïli 1 Jean-Paul Haton 1
1 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : The objective of this paper is to present a large study concerning the use of distant language models. In order to combine efficiently distant and classical models, an adaptation of the back-off principle is made. Also, we show the importance of each part of a history for the prediction. In fact, each sub-history is analyzed in order to estimate its importance in terms of prediction and then a weight is associated to each class of sub-histories. Therefore, the combined models take into account the features of each history's part and not the whole history as made in other works. The contribution of distant n-gram models in terms of perplexity is significant and improves the results by 12.8%. Making the linear combination depending on sub-histories achieves an improvement of $5.3\%$ in comparison to classical linear combination.
Type de document :
Communication dans un congrès
8th European Conference on Speech Communication and Technology - Eurospeech'03, Sep 2003, Genève, Switzerland. 1, pp.409-412, 2003
Liste complète des métadonnées

Littérature citée [8 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00099595
Contributeur : Publications Loria <>
Soumis le : mercredi 22 novembre 2017 - 11:53:48
Dernière modification le : jeudi 11 janvier 2018 - 06:19:57

Fichier

eurospeech2003_2.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00099595, version 1

Collections

Citation

David Langlois, Kamel Smaïli, Jean-Paul Haton. Efficient linear combination for distant n-gram models. 8th European Conference on Speech Communication and Technology - Eurospeech'03, Sep 2003, Genève, Switzerland. 1, pp.409-412, 2003. 〈inria-00099595〉

Partager

Métriques

Consultations de la notice

234

Téléchargements de fichiers

23