Blackcompass

BlackcompassDate: 04/2016 – 04/2018Funding: Région Pays de la LoireCall: Fonds Pays de la Loire Territoires d’InnovationPartners: Dictanova (France), Ville de Nantes (France)URL: https://lium.univ-lemans.fr/en/blackcompass/LIUM Participant(s): Sylvain MeignierAntoine LaurentThe project aims to develop a software solution to valorize phone exchange content between consumers and brands by analyzing this content.

Alexis Conneau

Learning and applications of distributed multilingual representationsStarting: 01/10/2015PhD Student: Alexis ConneauAdvisor(s): Paul Deléglise (LIUM, LST)Co-advisor(s): Loïc Barrault (LIUM, LST), Holger Schwenk (Facebook)Funding: CIFRE (Facebook)Learning and applications of distributed multilingual representations

M2CR

Multilingual Multimodal Continuous Representation for Human Language Understanding (M2CR)Date: 06/2015 – 06/2019Funding: AutresCall: ChisteraPartners: MILA (Canada), CVC (Espagne)URL: https://projets-lium.univ-lemans.fr/m2crLIUM Participant(s): Loïc BarraultFethi BougaresNathalie CamelinYannick EstèveMercedes García MartínezSahar GhannayAdrien BardetCommunication is one of the necessary condition to develop intelligence in living beings. Humans use several modalities to exchange information: speech, written text, both in many languages, […]

JOKER

JOKe and Empathy of a Robot/ECA: Towards social and affective relations with a robot (JOKER)Date: 01/2014 – 07/2017Funding: EU H2020Call: CHIST-ERA 2012Partners: LIMSI (coordinateur) (France), UCD (Irlande), UMONS (Belgique), KOC University (Turquie)URL: https://lium.univ-lemans.fr/en/joker/LIUM Participant(s): Yannick EstèveNathalie CamelinSimon PetitrenaudSylvain MeignierDaniel LuzzatiThis project will build and develop JOKER, a generic intelligent user interface providing a multimodal dialogue […]

EUMSSI

Event Understanding through Multimodal Social (EUMSSI)Date: 11/2013 – 10/2016Funding: EU FP7Call: ICT-2013.4.1 Content analytics and language technologiesPartners: UPF (Spain), L3S (Germany), VSN (Spain), GFaI (Germany), IDIAP (Switzerland)URL: https://www.eumssi.eu/LIUM Participant(s): Yannick EstèveVincent JousseSylvain MeignierPaul DelégliseNathalie CamelinL’objectif principal de EUMSSI est de développer des technologies d’identification et d’agrégation d’informations non structurées provenant de sources de nature très […]

Abdessalam Bouchekif

Automatic structuring of audio documentsStarting: 01/10/2012PhD Student: Abdessalam BouchekifAdvisor(s): Yannick EstèveCo-advisor(s): Nathalie CamelinFunding: Contrat Orange LabsThe topic structuring is an area that has attracted much attention in the Natural Language Processing community. Indeed, topic structuring is considered as the starting point of several applications such as information retrieval, summarization and topic modeling. In this thesis, […]

VERA

AdVanced ERror Analysis for speech recognition (VERA)Date: 01/2013 – 01/2015Funding: ANRCall: BlancPartners: LNE (France), LPP (France), LIMSI (France)URL: https://lium.univ-lemans.fr/en/vera/LIUM Participant(s): Nathalie CamelinDaniel LuzzatiPaul DelégliseSylvain MeignierYannick EstèveThe VERA project aims at developing tools for diagnostic, localization, and measurements of automatic transcription errors. This project is based on a consortium of first-rate academic actors in this field. […]

CSLM

Software: Continuous Space Language Model toolkit (CSLM)GitHub: https://git-lium.univ-lemans.fr/barrault/cslmURL: https://git-lium.univ-lemans.fr/barrault/cslm/-/archive/master/cslm-master.tar.gzAuthor(s): Holger SchwenkCSLM toolkit is open-source software which implements the so-called continuous space language model. The basic idea of this approach is to project the word indices onto a continuous space and to use a probability estimator operating on this space. Since the resulting probability functions are […]

MANY

Corpus: MANYLicence: GNU GPL v3URL: https://code.google.com/archive/p/many/Many is a MT System Combination software which architecture is described in the following picture :     The combination can be decomposed into three steps 1-Best hypotheses from all M systems are aligned in order to build M confusion networks (one for each system considered as backbone). All cn […]