Efficient linear combination for distant n-gram models - Archive ouverte HAL Access content directly
Conference Papers Year : 2003

Efficient linear combination for distant n-gram models


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.
Fichier principal
Vignette du fichier
eurospeech2003_2.pdf (119.44 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00099595 , version 1 (22-11-2017)


  • HAL Id : inria-00099595 , version 1


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. pp.409-412. ⟨inria-00099595⟩
116 View
57 Download


Gmail Facebook Twitter LinkedIn More