NéoDate: 02/2018 – 01/2020Funding: RFI AltanStic 2020Call: Amorçage, Défis scientifique 2017Partners: Laboratoire ERIC (France), CRTT (France)URL: https://lium.univ-lemans.fr/en/neo/LIUM Participant(s): Nicolas DuguéNathalie CamelinNeo is an interdisciplinary digital humanities research project aiming at the semi-automatic detection and analysis of contemporary neology. It results from the convergence of new language practices of the modern web (creation of new words […]
Neural approaches for abstractive text summarizationStarting: 01/09/2017PhD Student: Paul TardyAdvisor(s): Yannick Estève (LIUM – LST)Co-advisor(s): Funding: CIFRE, Financière du CaroubierThis thesis aims at developping Neural approaches for abstract summarization of speech transcripts with a view to developing an automatic solution for abstract summarization of speech transcripts.
News.bridgeDate: 01/2018 – 06/2019Funding: GoogleCall: Digital News Innovation FundingPartners: Deutsche Welle, Latvian News Agency, PriberamURL: https://lium.univ-lemans.fr/en/news-bridge/LIUM Participant(s): Sahar GhannayNatalia TomashenkoYannick EstèveThe NEWS-BRIDGE project will build a commercially exploitable integrated tool with a complete workflow using language technologies to facilitate and enhance multilingual news production. This tool provides for a full broadcast news translation system, rendering […]
Autonomous Lifelong Learning IntelligEnt Systems (ALLIES)Date: 12/2017 – 03/2022Funding: EU H2020Call: chist-eraPartners: IDIAP (Switzerland), UPC (Span), LNE (France)URL: https://projets-lium.univ-lemans.fr/alliesLIUM Participant(s): Anthony LarcherLoïc BarraultFethi BougaresSylvain MeignierYevhenii ProkopaloMeysam ShamsiThe goal of the ALLIES project is to encourage and demonstrate the development of autonomous systems, able to sustain performance across time according to a given learning scenario. A […]
Corpus: Topic Segmentation (FrNewsLink)URL: https://hal.archives-ouvertes.fr/hal-01741177FrNewsLink package allows to adress several applicative tasks in the domain of topic and titling segmentation. It is compososed of a set of resources from a varied corpus of French Broadcast News (BN) and press articles. Due to broadcasting rights, this package does not contain videos or audios files. The corpus […]
Deep neural networks for oral and written language processing (RAPACE)Date: 10/2017 – 09/2020Funding: RFI AltanStic 2020Call: Défis scientifiques 2016Partners: LINA (France)URL: https://lium.univ-lemans.fr/en/rapace/LIUM Participant(s): Antoine CaubrièreAntoine LaurentYannick EstèveThe RAPACE project focuses on the implementation of a deep neural architecture, associating specialized hidden layers, to develop a fully neural system of speech processing. The aim is to […]
Soutenance de thèse, Gaël LE LAN Titre : Analyse en locuteurs de collections de documents multimédia. Composition du jury : Guillaume GRAVIER, DR CNRS, IRISA, Président, Claude BARRAS, MCF HDR, Paris XI, Rapporteur, Jean-François BONASTRE, PR, Université d’Avignon, Rapporteur Corrine FREDOUILLE, MCF HDR, Université d’Avignon, Sylvain MEIGNIER, Le Mans Université, Directeur de thèse, Delphine CHARLET, […]
Transdisciplinary Analysis of French Newsreels (1945-1969) (Antract)Date: 10/2017 – 03/2022Funding: ANRCall: GenericPartners: INA (France), EURECOM (France), Voxolab (France), CHS (France)URL: https://lium.univ-lemans.fr/en/antract/LIUM Participant(s): Simon PetitrenaudAntoine LaurentSylvain MeignierPierre-Alexandre BrouxThe general objective of the ANTRACT project is the analysis of the images and sounds produced weekly in the framework of an independent company created in 1945, les Actualités […]
PhD defence, Sahar GHANNAY Title : A study of continuous word representations applied to ASR error detection. Composition of the jury : Présidente : Martine Adda-Decker, Reviewers : Sophie Rosset, Frédéric Béchet, Examiners : Benoit Favre, Benjamin Lecouteux, Supervisor : Yannick Estève Co-supervisor : Nathalie Camelin Abstract : This thesis concerns a study of continuous […]
Deep neural networks for oral and written language processingStarting: 04/09/2017PhD Student: Antoine CaubrièreAdvisor(s): Yannick Estève (LIUM, LST)Co-advisor(s): Antoine Laurent (LIUM, LST) & Emmanuel Morin (LS2N)Funding: RAPACE ProjectThe aim of this thesis is to develop a named entity recognition system in an audio stream that will rely solely on a deep neural network. Until now, this […]
Français