The LIUM Human Active Correction Platform for Speaker Diarization The human assisted speaker diarization platform enables a human annotator to correct the output of any speaker diarization system by providing a graphical view of the diarization segmentation and clustering steps and guiding the human annotator to optimize the correction process and easily improve […]
Seminar from diarization team Date: 21/05/2021 Time: 11h00 Localization: online Speakers: Meysam Shamsi, Yevhenii Prokopalo and Anthony Larcher Human assisted speaker diarization, approach and demonstrator ALLIES and ESPERANTO projects are targeting human assisted speaker diarization across time. To address this task step by step, our team proposes a within-show human assisted correction […]
Seminar from Valentin Pelloin, PhD student at LIUM Date: 12/05/2021 Time: 11h00 Localization: online Speaker: Valentin Pelloin End2End Acoustic to Semantic Transduction We propose a novel end-to-end sequence-to-sequence spoken language understanding model using an attention mechanism. It reliably selects contextual acoustic features in order to hypothesize semantic contents. An initial architecture capable […]
The paper SINr: fast computing of Sparse Interpretable Node Representations is not a sin! recieved the best paper award at the 19th Symposium on Intelligent Data Analysis (IDA 2021). Congrats to Thibault Prouteau, Victor Connes, Nicolas Dugué, Anthony Perez, Jean-Charles Lamirel, Nathalie Camelin and Sylvain Meignier !
Seminar from Thibault Prouteau, PhD student at LIUM Date: 19/04/2021 Time: 11h00 Localization: online Speaker: Thibault Prouteau SINr: fast computing of Sparse Interpretable Node Representations is not a sin! While graph embedding aims at learning low-dimensional representations of nodes encompassing the graph topology, word embedding focus on learning word vectors that encode […]
Seminar from Gaëtan Caillaut, Post-Doctoral researcher at LIUM Date: 12/03/2021 Time: 11h00 Localization: online Speaker: Gaëtan Caillaut MiniBERT: a simple and explainable BERT model As part of the PolysEmY project, we work with the SNCF (French railway company) to produce “polysemic-aware” word embeddings. Documents provided by the SNCF are written in technical […]
Seminar by Adrien Bardet, PhD Student at LIUM, Team LST Date: 19/02/2021 Time: 11h00 Localization: online Speaker: Adrien Bardet Multilingual neural architectures for natural language processing Machine translation using little data leads to poor performance. The use of multilingual systems is one solution to this problem. Multilingual machine translation systems make it […]
PhD defence, Adrien Bardet Date : 22/02/2021 Time : 14h00 Location : IC2 building, LIUM, Le Mans Université, online Title: Multilingual neural architectures for natural language processing Jury members: Ms. Claire Gardent, Professor, LORIA, Vandoeuvre-lès-Nancy, Reviewer Mr. Alexandre Allauzen, Professor, LAMSADE, Paris, Reviewer Mr. Emmanuel MORIN Professor, Université de Nantes – LS2N, Examiner Mr. […]
Corpus: PASTEL (Corpus PASTEL)Author(s): Salima MdhaffarYannick EstèveAntoine LaurentNathalie CamelinLe corpus PASTEL consiste en une collection de cours de différents domaines informatique (traitement automatique des langues, introduction à l’informatique, etc) en première année de licence d’informatique à l’Université de Nantes. Il est constitué de cours qui proviennent de deux sources : le projet COCo (Comin Open […]
Proposal of an approach for capitalizing on indicators dedicated to a study of the impact of the system for improving the French language, écri+.Starting: 04/01/2021PhD Student: Albane GrilAdvisor(s): Sébastien George Co-advisor(s): Madeth May (LIUM), Valérie Renault (CREN)Funding: PIA Ecri+Contexte de la thèse : Le projet national PIA écri+ est dédié à l’accompagnement des étudiants dans […]
Français