Research
My main interest is in multilingual Natural Language Processing jointly with Deep Learning for Information Retrieval.
I focus on modeling context for several fields of NLP: Spoken Language Understanding, semantic content analysis and modeling, machine translation, Intent Detection in real-life application at scale.
Teaching
Since years I'm giving NLP courses to master or engineer students for instance:
- EPITA - International Program (since 2019)
- Polytech Grenoble - MOSIG - International Programm (2016)
... and many other computer science courses such like programming, databases, etc.
Management
I am Research Manager at Qwant, Deputy Director of the QWANT-INRIA lab, head of the NLP team at QWANT.
I'm also part of the 3IA Nice côte d'Azur board and member of the board of French scientific associations:
Biography
NLP Research Scientist and Manager at QWANT since 2017. Deputy director of the INRIA-QWANT Lab since 2018.
Before joining Qwant, he was applied researcher at SYSTRAN to work on domain adaptation for NMT (2016-2017), member of the GETALP team at the University of Grenoble to develop Deep Learning approaches for SMT evaluation (2015-2016), part of the Xerox Research Centre Europe (XRCE) in the Machine Learning for Document Access and Translation (MLDAT) group (2013-2015), postdoc researcher in the Speech and Language Technology group at the laboratory of the University of Le Mans, France (LIUM), research engineer at the Vision & Content Engineering Laboratory at the CEA LIST (2009-2010).
He received a PhD in Computer Science from the University of Avignon, France in 2008.
Latest news
-
NEW: the FrALBERT model is available on HuggingFace, check this out! https://huggingface.co/qwant/fralbert-base
- Oralie cattan, Christophe Servan and Sophie Rosset. On the Usability of Transformers-based models for a French Question-Answering task. In Proceedings of Recent Advances in Natural Language Processing (RANLP2021), Varna, Bulgaria, September 2021. [PDF]
- Oralie cattan, Christophe Servan and Sophie Rosset. On the cross-lingual transferability of multilingual prototypical models accorss NLU tasks. In Proceedings of Meta Learning and Its Applications to Natural Language Processing, workshop at ACL 2021 (METANLP'2021), Bangkok, Thailand, August 2021. [PDF]
- Sahar Ghannay, Christophe Servan and Sophie Rosset. Neural Networks approaches focused on French Spoken Language Understanding: application to the MEDIA Evaluation Task. In Proceedings of The 28th International Conference on Computational Linguistics (COLING'2020), Barcelona, Spain, December 2020. [PDF]
Contact
QWANT: https://www.qwant.com
Address:
QWANT
Immeuble Crystal Park
63 Rue de Villiers
92200 Neuilly-sur-Seine, France.
Phone: +33 (0)1 83 64 89 37
Email: c dot servan at qwant dot com
- Social networks:
Last updated on 2021-07-18