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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download

https://hal.inria.fr/inria-00099595
Contributor : Publications Loria <>
Submitted on : Wednesday, November 22, 2017 - 11:53:48 AM
Last modification on : Thursday, January 11, 2018 - 6:19:57 AM

File

eurospeech2003_2.pdf
Files produced by the author(s)

Identifiers

  • 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. pp.409-412. ⟨inria-00099595⟩

Share

Metrics

Record views

259

Files downloads

35