Fast Evaluation and Connectionist Language Models

Date: 
31/08/2010
Heure: 
15h30
Orateur: 
F. Zamora-Martinez
Laboratoire: 
Universidad CEU-Cardinal Herrera and Universidad Politecnica de Valencia
Groupe: 
Traduction
Résumé du séminaire: 
Connectionist language models offer many advantages over their statistical counterparts, but they also have some drawbacks like a much more expensive computational cost. This work describes a novel method to overcome this problem. A set of normalization values associated to the most frequent n-grams is pre-computed and the model is smoothed with lower n-gram connectionist or statistical models. The proposed approach is favourably compared to standard connectionist language models and with statistical back-off language models.
PDF 1: 
http://lium3.univ-lemans.fr/lium_d5/sites/default/files/traspas.pdf