My research topics concern machine learning applications to health data, including:
- Natural Language Processing (personal health records, social networks, etc.)
- Image classification and object detection (i.e. microscopy)
- Other kind of data (spectrometry, biological data...)
I teach Computer Science and am manager of the master's program Applied Mathematics and Computer Science (MAIN) at Polytech Sorbonne.
Short bio
- Since January 2024: Director of Limics
- Since September 2017: Full professor at Sorbonne Université (formerly known as Université Pierre et Marie Curie — UPMC, Paris 6) and Limics; I'm teaching at Polytech Paris-Sorbonne.
- 2014: Habilitation à diriger des recherches (HDR*)
- 2007-2017: Assistant Professor at University Paris-Sud and LIMSI-CNRS, team ILES.
- 2006-2007: Postdoc, Xerox Research Center Europe, where I worked on temporal processing and semantic representation in texts.
- 2003-2006: PhD, École Nationale Supérieure des Mines de Saint-Etienne (ENSM-SE), centre G2I, department RIM, team COCRI: Extraction et recherche d'information en langage naturel dans les documents semi-structurés (defended on September 27th, 2006).
- 2003: Master Thesis, Institut de Recherche de Informatique de Toulouse (IRIT), Team LiLac: Calcul des relations temporelles dans le discours (thesis)
- 2000-2002: Graduate engineering School in Computer Science, INSA de Toulouse
PhD supervision (current and past)
- Ariel Cohen (2024-), with Emmanuelle Kempf (APHP)
- Alaedine Benani (2024-), with Zoī and Emmanuel Messas (HEGP)
- Adam Remaki (2023-), with Christel Gérardin (Bichat Hospital)
- Marco Naguib (2022-), with Aurélie Névéol (LISN-CNRS, fka LIMSI)
- Manon Chossegros (2022-), with Daniel Stockholm (APHP, CRSA)
- Aniss Acherar (2020-2024), with Renaud Piarroux (APHP, Sorbonne Université)
- Nesrine Bannour (2020-2023), with Aurélie Névéol (LIMSI-CNRS) and Bastien Rance (APHP, Université de Paris)
- Noshine Mohammad (2020-2023), with Renaud Piarroux (APHP, Sorbonne Université)
- Emmanuelle Kempf (2021-2023), with Christel Daniel (APHP, Limics)
- Perceval Wajsbürt (2018-2021), with Christel Daniel (APHP, Limics)
- Chyrine Tahri (2020-2023), with Erdyn
- Swen Ribeiro (2016-2020), with Olivier Ferret (CEA-LIST)
- Tien-Duc Cao (2016-2019), with Ioana Manolescu (INRIA)
- Sergio Torres (2015-2019), with Pierre Chastang (UVSQ)
- Julien Tourille (2015-2018), with Aurélie Névéol (LIMSI-CNRS) and Olivier Ferret (CEA-LIST)
- Clément de Groc (2010-2013), with Syllabs
- Béatrice Arnulphy (2009-2012), with Anne Vilnat (LIMSI-CNRS)
Bulk resources
- Slides from my talk on "the challenges of industrializing Natural Language Processing for health data" for the International Symposium CITADEL (Apr. 2025)
- Slides from my introductory lesson to Large Language Models for the Annual Meeting of the Doctoral School Pierre Louis of Public health in Saint-Malo (Feb. 2024)
- Slides from my seminar on how to use Large Language Models for resource curation (at Orphanet, Sept. 2024)
Slides from my introductory lesson to NLP (in French) at the ETAL 2023 summer school in Marseille
Slides from our tutorial on Computational Fact-Checking (a content management perspective) at VLDB in Rio (I. Manolescu).
Funding
- WP leader and scientic leader for Limics in the BPI-funded project PARTAGES, (call2024-2026)
- Co-PI of the RHU "AI-Triomph" (Artificial Intelligence – clinical TRIals Optimization for oncology with Multimodal PatHology). RHU (hospital-university research) are programs of excellence supported by by the French National Research Agency (ANR, 2023-2028).
- Coordinator of an action in the SN@SU project, a vast digital health training program at Sorbonne University (2023-2028)
- Scientific leader for Limics in the European project European Cancer Imaging Initiative (EUCAIM) (2023-2027)
- Scientific leader for Limics in the ANR project CDE.AI (2022-2028)
- Principal investigator of the Google Digital News Initiative project on interactive annotation and machine learning for data journalists (2017-1018)
- Principal investigator of the ANR project ASRAEL (2015-2020)
- Principal investigator (together with Ioana Manolescu, INRIA) of a Google Award for Computational Journalism (2015-2016)
- Scientific leader for LIMSI in the ANR project ContentCheck (2015-2020)
- Principal investigator of Digitéo project ASTRE (2013-2015)
- Scientific leader for LIMSI in the ANR project Contint Chronolines (2011-2014)
Besides, I participated in many other research projects as a team member.
Duties
- Since 2024: Director of Limics
- Since 2019: Head of the master's program "Applied Mathematics and Computer Science" (Mathématiques Appliquées et Informatique, MAIN) at Polytech Sorbonne
- Since 2018: Elected member of the "Conseil de l'École" (~ executive board) at Polytech Sorbonne
- Since 2021: Member of the Scientific Committee at "UFR d'Ingénierie", Faculty of Sciences, Sorbonne University
- Since 2025: Member of the board of the Doctoral School 393 "Pierre Louis de Santé Publique : Epidémiologie et Sciences de l'Information Biomédicale"
Former duties
At Limics:
- 2019-2023: Member of Limics executive board
At Sorbonne University:
- 2017-2019: Co-manager of the computer science teachings at Polytech-Sorbonne
At University Paris-Sud, I was:
- From 2009 to 2017: teaching manager (responsable pédagogique) of Licence 3 MIAGE at UFR de Sciences, Univ. Paris-Sud
- From 2012 to 2017: teaching manager (responsable pédagogique) for the speciality "computer science", in the 3rd year of Polytech Paris-Sud en apprentissage (apprenticeship)
- 2015-2017: Elected member of the "Conseil de Département d'Informatique de la faculté des sciences d'Orsay" (~ executive board of the Computer Science Department)
- 2014-2017: Elected member of the "Conseil de Gouvernance" (~ executive board) at Polytech Paris-Sud
- 2010-2017: Elected member of the "Commission Consultative de Spécialistes de l'Université (CCSU)" in Computer Science at Univ. Paris-Sud (chooses the scientific committees for new tenure positions, follows staff careers, etc.).
- 2014-2017: Elected member of the board of the "Commission Consultative de Spécialistes de l'Université (CCSU)" in Computer Science at Univ. Paris-Sud.
- 2015-2017: Ex-officio member of the "Conseil de Perfectionnement de la Licence d'Informatique" (~ educational board at bachelor's level)
- 2013-2017: Member of the "cellule informatique" at Polytech Paris-Sud (a small committee focused on IT issues in the school)
- 2008-2014: Member of the "Conseil de Laboratoire" (lab council) at LIMSI