The LIUM present at the Science Fair Date: 15 and 16 october 2022 Time: 10h00 – 18h00 Location: Le Mans (Abbaye de l’Epau) and Laval (Laval Virtual Center) More information and complet programme in Sarthe and in Mayenne In Le Mans : AI and climate change: incompatible? The LIUM is specialized in the automatic […]
Seminar from Valentin Pelloin and Martin Lebourdais, PhD students at LIUM Date: 14/10/2022 Time: 11h00 Localization: IC2 Boardroom, Speakers: Valentin Pelloin et Martin Lebourdais ASR-Generated Text for Language Model Pre-training Applied to Speech Tasks Valentin Pelloin We aim at improving spoken language modeling (LM) using very large amount of automatically transcribed […]
Interpretability of embeddingsStarting: 01/10/2022PhD Student: Simon GuillotAdvisor(s): Antoin Laurent (LIUM) Co-advisor(s): Nicolas Dugué (LIUM), Mathieu Valette (INALCO)Funding: ANR DIGINGDescritpion Les approches de plongements lexicaux (word embedding en anglais) ont pour objectif de représenter le vocabulaire de la langue sous forme de vecteurs intelligibles par la machine. En particulier, l’une des hypothèses derrière le succès de […]
LST day On October 6th, the day of the LST team takes place. On this occasion, researchers – the young and the more experienced – present their research themes.
The LIUM at the European Researchers’ Night Date: 30/09/2022 Time: de 18h to midnight Localization: Les Quinconces See the Complet programme THE UNEXPECTED IN ARTIFICIAL INTELLIGENCE SYSTEMS Artificial intelligence is present in our daily lives. These technologies based on learning models from data allow machines to perform complex tasks. We believe that machines and their […]
Traduction multilingue de la parole sous contraintes de ressources Encadrant(e)s: Antoine Laurent, Professeur des Universités Equipe d’accueil : LIUM – LST Lieu : Le Mans Contact : Antoine.Laurent(at)univ-lemans.fr Contexte : Ce travail de postdoc s’inscrit dans le domaine du traitement automatique des langues (TAL) et plus particulièrement de la traduction automatique de la parole […]
Magazine Decryptage : Risks and uncertainty
Magazine Decryptage : Risks and uncertainty
Seminar from Mohamed Ettaleb, Post-doctoral fellow at LIUM Date: 01/07/2022 Time: 10h30 Localization: IC2 Boardroom, online Speaker: Mohamed Ettaleb Evaluation of weakly-supervised methods for aspect extraction Aspect-based sentiment analysis (ABSA) may provide more detailed information than general sentiment analysis. It aims to extract aspects from reviews and predict their polarities. In […]
PhD defence, Manon Macary Date : 24/06/2022 Time : 14h00 Location : IC2, Boardroom and online Title : Massive and real-time data analysis in order to extract semantic and emotional information from speech Jury members : Ms. Martine ADDA-DECKER, Directrice de Recherche, LPP – CNRS-Sorbonne Nouvelle, Reviewer Mr. Denis JOUVET, Directeur de recherche, […]
Français