Seminars

On 2013-02-21 at 3.00 pm:
   Bouchekif, A. (OrangeLabs)
Segmentation thématique, Analyse automatique de la parole dans les flux audio

Summary PDF

On 2012-12-04 at 10.00 am:
   Rico Sennrich (LIUM - Traduction)
A Multi-Domain Translation Model Framework for Statistical Machine Translation

On 2012-03-14 at 10.30 am:
   Rico Sennrich (Institute of Computational Linguistics, University of Zurich)
Quick and painless domain adaptation for SMT

Summary

On 2011-11-16 at 11.00 am:
   Patrik Lambert (LIUM - LST)
The MANY MT System Combination Tool at the ML4HMT Workshop Shared Task

Summary

On 2011-11-15 at 11.00 am:
   Huei-Chi Lin (Bitong - Université Catholique de Louvain)
Introduction au chinois moderne et à son traitement automatique

Summary PDF

On 2011-09-16 at 10.30 am:
   Waleed Oransa (IBM - Egypt, Le Caire)
Injected Linguistic Tags to Improve Phrase Based SMT

Summary PDF

On 2011-05-27 at 9.30 am:
   Marta Ruiz Costa-jussà (Barcelona Media Innovation Center - LST)
Statistical Machine Translation: ongoing research

Summary

On 2011-05-25 at 2.00 pm:
   Sofiane Medjkoune (IRCCyN - Nantes - LST)
Reconnaissance de symboles et expressions mathématiques: fusion de signaux écrits et sonores

Summary PDF

On 2011-03-24 at 3.30 pm:
   Mathieu MURATET (IRIT - Université Toulouse III - EIAH)
Conception et évaluation d'un jeu sérieux pour l'apprentissage des fondamentaux de la programmation

Summary PDF

On 2011-03-17 at 2.30 pm:
   Christophe Lévy (LIA - Avignon - Parole)
Modélisation acoustique : application à la transcription et à la reconnaissance du locuteur

PDF

On 2010-10-11 at 2.00 pm:
   Elie Khoury (LIUM - Salle des conseils - LST)
Indexation vidéo non-supervisée basée sur la caractérisation audiovisuelle des personnes

Summary PDF

On 2010-08-31 at 3.30 pm:
   F. Zamora-Martinez (Universidad CEU-Cardinal Herrera and Universidad Politecnica de Valencia - Traduction)
Fast Evaluation and Connectionist Language Models

Summary PDF
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.

On 2010-04-08 at 11.00 am:
   Kolár, J. (LIMSI - Groupe Traitement du Langage Parlé)
Speaker adaptation of language and prosodic models for automatic dialog act segmentation of speech

Summary

On 2010-03-09 at 11.00 am:
   Estève, Y. (LIUM - équipe Parole/Traduction)
Introduction aux systèmes de traduction basés sur les séquences de mots hiérarchiques

Summary PDF

On 2010-02-19 at 10.30 am:
   Mauclair, J. (Laboratoire d'Informatique Paris-Descartes - équipe DIADEX)
Fiabilité d'un SRAP

Summary PDF

On 2010-02-19 at 10.30 am:
   Janiszek, D. (Laboratoire d'Informatique Paris-Descartes - équipe DIADEX)
La standardisation des applications vocales orientées services.

Summary PDF