Research

My research interests include:

Reviewing

2021: EACL
2020: ACL, ETeRNAL, TALN, COLING, EMNLP (Area Chair Machine Translation)
2019: NAACL (Area Chair, Sequence Labeling & Parsing), TALN, TACL, *SEM, ACL, EMNLP
2018: NAACL, IJCAI, ICML, COLING, QEAPE, ACL, TALN, Odyssey, EMNLP, TACLp
2017: EACL, ACL, TALN, EMNLP, NIPS, IWSLT
2016: NAACL, ACL, TALN, InterSpeech, Coling, Rep4NLP
2015: BUCC, AAAI, IATIS, TALN, TAL, TACL, Interspeech, IJCAI, Errare, WPTP, IWSLT
2014: Interspeech, CVSC, TALN, BUCC, TACL, MT Journal, WMT, LNE
2013: TALN, Interspeech, CVSC, TAL
2012: NAACL, TALN
2011: TALN
2010: ICTAI, TALN, CORIA

2020: comité de sélection poste n°0778 (Université Sorbonne Nouvelle & ESIT)
2019: comité de sélection poste n°0588 (Paris 8) et n°1631 (Paris Sud)
2018: comité de sélection poste n°2228 (IUT d'Orsay), ANR appel à projet générique (CE23)
2016: ANR Jeune Chercheur
2015: ANR Jeune Chercheur
2014: examinateur de la thèse de Ngoc Quang Luong intitulée Word Confidence Estimation and Its Applications in Statistical Machine Translation (sous la direction de Laurent Besacier et de Benjamin Lecouteux)

Responsabe de l'axe 2 du GDR LIFT (Linguistique et évaluation des systèmes de traitement automatique des langues)
Secretary of ATALA
Board member of Paris Sud recruiting committee for Computer Science (vice-président de la CSSU 27) : 2017-2019

Current:

José Carlos Rosales: Machine Translation for User Generated Content (since January 2018)
Margot Lacour: Second Language Acquisition Modeling (since September 2018)

Past:

Elena Knyazeva: Imitation learning for structured prediction and machine translation (October 2013 -- May 2018)
Lauriane Aufrant: Cross-lingual dependency parsing (October 2014 -- April 2018) [pdf]

Tristan Sandras (L2, 2011): website for SMS translation
Diaa Al Mohamad (M2, 2011): connection between structured learning and ranking
Elena Knyazeva (M2, 2013): SEARN for Machine Translation
Adrien Cabaco (IUT, 2013): Extracting Post-Editions from Word documents
Wang Xin (M1, 2013): Generalizing DTW for multiple signals
Oana Jean-Marie (M2, 2014): Imitation learning for Dependency Parsing
Margot Lacour (M1, 2017): Domain adaptation for machine translation
Éléonor Bartenlian (M1, 2017: Domain adaptation ofr PoS tagging
Nicolas Devatine (L3, 2018): word segmentation for twitter
Jiaxin Gao (M1, 2018): domain adaptation for dependency parsing
Julie Tytgat (M2, 2019): measuring the similarity between sentences
Valentin Carpentier (M2, 2019): automatic generation of program code from their description
Benjamin Vallois (M2, 2020): Utilisation d'a priori linguistique pour faciliter le développement d'un analyseur multilingue en dépendances
Bingzhi Li (M2, 2020): Traduction automatique des marqueurs temporels chinois en français

Here is the full list of the projects I have been involved in:

Errator (2018): plateforme d’aide à l’annotation morpho-syntaxique (AAP Université Paris Saclay, PI, 25 000€)
FLOwCON (ANR Astrid): Contrôle d'écoulements turbulents en boucle fermée par apprentissage automatique
ParSiTi (2016-2020): parsing and translating user generated content, with INRIA and LIPN (co-PI)
Odessa (2015-2018): Online Diarization Enhanced by recent Speaker identification and Structured prediction Approaches, with Eurecom and Odessa
Papyrus (2015-2017) domain adaptation for PoS tagging and dependency parsing
Transread (2012-2015): enriching bilingual reading and interaction with cross-lingual alignments
Trace (2010-2013): analyzing and correcting errors in MT
Quaero (2008-2013)
CROTAL (2007-2009) on conditional random fields for natural language.
Marmota (2005--2009) on statistical machine learning and tree structured data.
Atash (2006-2009) on automatic document transformations with structured prediction approaches.
ACI MDD (ACI)

Do not hesitate to contact me if you are interested in working in applying machine learning to NLP problem.