F
Fabrice Lefèvre
Researcher at University of Avignon
Publications - 141
Citations - 1867
Fabrice Lefèvre is an academic researcher from University of Avignon. The author has contributed to research in topics: Spoken language & Reinforcement learning. The author has an hindex of 22, co-authored 139 publications receiving 1777 citations. Previous affiliations of Fabrice Lefèvre include Centre national de la recherche scientifique & University of Cambridge.
Papers
More filters
Journal ArticleDOI
Comparing Stochastic Approaches to Spoken Language Understanding in Multiple Languages
Stefan Hahn,Marco Dinarelli,Christian Raymond,Fabrice Lefèvre,Patrick Lehnen,R. De Mori,Alessandro Moschitti,Hermann Ney,Giuseppe Riccardi +8 more
TL;DR: Six different modeling approaches are investigated to tackle the task of concept tagging, including classical, well-known generative and discriminative methods like Finite State Transducers, Statistical Machine Translation (SMT), Maximum Entropy Markov Models (MEMMs), or Support Vector Machines (SVMs).
Journal ArticleDOI
Alanine-stretch scanning mutagenesis: a simple and efficient method to probe protein structure and function
TL;DR: A foolproof method to substitute a stretch of residues by alanines to create two alanine codons andcision of the resistance gene byPvuII yields the correct insertion of codons is developed.
Proceedings Article
User Simulation in Dialogue Systems Using Inverse Reinforcement Learning.
TL;DR: A novel approach for user simulation based on Inverse Reinforcement Learning (IRL) is outlined, which aims at simulating human users in order to generate synthetic data.
Patent
Method for obtaining in vitro recombined polynucleotide sequences, sequence banks and resulting sequences
TL;DR: In this article, a method for producing recombined polynucleotide sequences from a bank of double-strand sequences was proposed. But this method is not suitable for the case of DNA sequences.
Proceedings Article
Results of the French Evalda-Media evaluation campaign for literal understanding
Hélène Bonneau-Maynard,Christelle Ayache,Frédéric Béchet,Alexandre Denis,Anne Kuhn,Fabrice Lefèvre,Djamel Mostefa,Matthieu Quignard,Sophie Rosset,Christophe Servan,Jeanne Villaneau +10 more
TL;DR: The MEDIA protocol for speech understanding evaluation is presented and the results of the June 2005 literal evaluation campaign are described and a diagnosis analysis of these results is proposed.