Factored Neural Machine TranslationStarting: 01/10/2014PhD Student: Mercedes García MartínezAdvisor(s): Yannick Estève (LIUM, LST)Co-advisor(s): Loïc Barrault (LIUM, LST) & Fethi Bougares (LIUM, LST)Funding: This work was partially funded by the French National Research Agency (ANR) through the CHIST-ERA M2CR project, under the contract number ANR-15-CHR2-0006-01Communication between humans across the lands is difficult due to the diversity […]
Event Understanding through Multimodal Social Stream InterpretationStarting: 01/10/2014PhD Student: Sahar GhannayAdvisor(s): Yannick Estève (LIUM – LST)Co-advisor(s): Nathalie Camelin (LIUM – LST)Funding: Région Pays de la Loire, EUMSSI (Event Understanding through Multimodal Social Stream Interpretation)This thesis concerns a study of continuous word representations applied to the automatic detection of speech recognition errors. Recent advances in the […]
Analyse en locuteurs de collections de documents multimédia.Starting: 01/04/2014PhD Student: Gaël Le LanAdvisor(s): Sylvain Meignier (LIUM – LST)Co-advisor(s): Anthony Larcher (LIUM – LST)Funding: Orange La segmentation et regroupement en locuteurs (SRL) de collection cherche à répondre à la question « qui parle quand ? » dans une collection de documents multimédia. C’est un prérequis indispensable […]
Multimodal Neural Machine TranslationStarting: 30/10/2014PhD Student: Ozan CaglayanAdvisor(s): Paul Deléglise (LIUM, LST)Co-advisor(s): Loïc Barrault (LIUM, LST) & Fethi Bougares (LIUM, LST)Funding: M2CR ProjectThis thesis aims at developing neural machine translation architectures by integrating different types of informations to improve the quality of the generated translations. More specifically, we are interested to guide the neural network […]
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 […]
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, […]
AdVanced ERror Analysis for speech recognition (VERA)Date: 01/2013 – 01/2016Funding: 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. […]
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 […]
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 […]
Français