Experience

LISN - Laboratoire Interdisciplinaire des Sciences du Numérique

• France
• Research Services
• 1 - 100 Employee

• Chercheur

  • Feb 2022 - Present

  Saclay, Île-de-France, France I joined the ILES teams to study Artificial Intelligence for Natural Language Processing (NLP) #AI #NLP.



Qwant

• France
• Technology, Information and Internet
• 1 - 100 Employee

• Research Manager

  • Sep 2019 - Present

  Paris, Île-de-France, France Manage and leading research projects and research team in NLP. Collaborations with product team to identify new use case. Leading project: - Intention Detection for web search engine at large scale - NLP for addTech & Shopping - Machine Translation for IR - NLU & Information Extraction (NER, PoS Tagging) for IR - Query auto-complete & auto-suggestion - 2 H2020 projects (AI4EU & SocialTruth), 2 ANR Projects (TextToKids & Kodicare) and 2 PIA projects (MOSS &… Show more Manage and leading research projects and research team in NLP. Collaborations with product team to identify new use case. Leading project: - Intention Detection for web search engine at large scale - NLP for addTech & Shopping - Machine Translation for IR - NLU & Information Extraction (NER, PoS Tagging) for IR - Query auto-complete & auto-suggestion - 2 H2020 projects (AI4EU & SocialTruth), 2 ANR Projects (TextToKids & Kodicare) and 2 PIA projects (MOSS & ANSWER)

• Qwant-INRIA Joint lab deputy director

  • Jul 2018 - Present

• Lead NLP & Research Scientist

  • Jan 2018 - Present

  Région de Paris, France My research mainly focuses on multilingual Natural Language Understanding for Information Retreival.



3IA Côte d'Azur

• Représentant des Entreprises au Comité de Pilotage du 3IA Côte d'Azur

  • Oct 2019 - Present

  Région de Nice, France



EPITA: Ecole d'Ingénieurs en Informatique

• France
• Higher Education
• 200 - 300 Employee

• NLP Professor

  • Jan 2019 - Dec 2022

  Paris et périphérie



SYSTRAN

• France
• Software Development
• 100 - 200 Employee

• Applied Researcher

  • Sep 2016 - Jan 2018

  Paris, France My main interest is to applied recent advances in Machine Learning (like Deep Learning approaches) to Mutilingual NLP. Mainly working on domain adaptation for NMT (OpenNMT project) and data mining from Tweeter (PAPYRUS project).



University of Joseph Fourier, Grenoble

• Higher Education
• 1 - 100 Employee

• Research Fellow

  • Mar 2015 - Aug 2016

  Région de Grenoble, France I'm involved in the KEHATH project, in which I apply Deep Learning approaches for NLP and especially for confidence measures (SMT and ASR).



Xerox

• United States
• Business Consulting and Services
• 700 & Above Employee

• Researcher

  • Sep 2013 - Feb 2015

  Région de Grenoble, France My main contribution concerns the TransLecture Project in order to study domain adaptation and incremental adaptation for Statistical Machine Translation. I also act as Dialogue System expert in a internal business project.



MateCat

• Italy
• Translation and Localization
• 1 - 100 Employee

• Chercheur - Post-doctorant

  • Sep 2012 - Aug 2013

  Within the framework of the MateCAT European Project (with the university of Le Mans - LIUM), I lead the research on user project adapation of the Translation Model.



Laboratoire d'Informatique de l'Université du Maine

• Chercheur - PostDoctorant

  • Nov 2010 - Aug 2013

  Le Mans, France My main topics are Statistical Machine Translation (SMT), Machine Learning (ML) and Natural Language Processing (NLP) and Information Retreival (RI). I mainly investigated Domain Adaptation, the use of Belief functions for feature estimation and the multi-criteria feature optimisation for SMT. I worked on the GALE (DARPA), BOLT (DARPA), EuroMatrixPlus (EU) and MateCAT (EU) projects.



CEA

• France
• Research Services
• 700 & Above Employee

• Chercheur - Ingénieur

  • Nov 2009 - Oct 2010

  Fontenay-aux-Roses, France Recruté dans le cadre du projet ANR WebCrossling, je suis responsable du Work Package final. Mon travail concerne la réalisation d'un système de traduction automatique utilisant des approches liant des méthodes formelles et des méthodes statistiques pour la recherche d'information.



Laboratoire Informatique d'Avignon (LIA), Avignon University

• Research Services
• 1 - 100 Employee

• ATER

  • Sep 2008 - Oct 2009

  Across language portability of a spoken language understanding system (SLU) deals with the possibility of reusing with moderate effort in a new language knowledge and data acquired for another language. The approach proposed in this paper is motivated by the availability of the fairly large MEDIA corpus carefully transcribed in French and semantically annotated in terms of constituents. A method is proposed for manually translating a portion of the training set for training an automatic… Show more Across language portability of a spoken language understanding system (SLU) deals with the possibility of reusing with moderate effort in a new language knowledge and data acquired for another language. The approach proposed in this paper is motivated by the availability of the fairly large MEDIA corpus carefully transcribed in French and semantically annotated in terms of constituents. A method is proposed for manually translating a portion of the training set for training an automatic machine translation (MT) system to be used for translating the remaining data. As the source language is annotated in terms of concept tags, a solution is presented for automatically transferring these tags to the translated corpus. Experimental results are presented on the accuracy of the translation expressed with the BLEU score as function of the size of the training corpus. It is shown that the process leads to comparable concept error rates in the two languages making the proposed approach suitable for SLU portability across languages.

• Thèse de Doctorat en Informatique

  • Sep 2005 - Sep 2008

  Avignon , France Mon travail de thèse m'amène à devenir expert dans le Traitement automatique du Langage Naturel Oral et plus précisément dans la compréhension de l'homme par la machine dans le dialogue Homme-Machine. Un exemple des applications directes de mes travaux est une interface téléphonique de réservation automatique de chambre d'hôtel. Je travaille sur des modèles de langages stochastiques appris sur des corpus mettant en jeu des outils tels que des grammaires formelles sous format FSM… Show more Mon travail de thèse m'amène à devenir expert dans le Traitement automatique du Langage Naturel Oral et plus précisément dans la compréhension de l'homme par la machine dans le dialogue Homme-Machine. Un exemple des applications directes de mes travaux est une interface téléphonique de réservation automatique de chambre d'hôtel. Je travaille sur des modèles de langages stochastiques appris sur des corpus mettant en jeu des outils tels que des grammaires formelles sous format FSM (librairie d'AT&T). J'ai participé activement à la campagne TECHNOLANGUE EVALDA/MEDIA, grace à laquelle j'ai pu développer mon expertise. Actuellement je travaille sur du routage d'appel, tâche qui s'apparente à de la classification/caractérisation d'appels.