Welcome to Synalp’s website !
The Synalp team is located in Nancy and is part of Loria, a research unit common to the French National Scientific Research Center (CNRS), the Université de Lorraine and Inria. Synalp belongs to Loria’s department 4 focusing on Natural Language Processing and Knowledge Discovery, and is affiliated with CNRS and Université de Lorraine.
Job (MCF) opportunity
An assistant professor (maître de conférences) position in computer science will open at University of Lorraine early 2024. Teaching will take place at the Institute of digital sciences, management, and cognition (IDMC). The successful candidate will join a research group of the departments D3, D4 ou D5 of the LORIA research lab. All relevant detailed information about this position will be posted online in due time. Potential applicants are encouraged to contact: - research: Stephan.Merz@loria.fr Stephan.Merz@loria.fr - teaching: Sylvain.Castagnos@loria.fr Sylvain.Castagnos@loria.fr
Important (in particular for applicants from abroad): applicants must usually be “qualified” for a position of assistant professor in France. For this academic year, the qualification process must be initiated before November 10 at 4pm.
Newly hired assistant professors typically have a reduced teaching load for at least the first year. It is expected that candidates are able to teach in French.
The Synalp team has been carrying research activities on Natural Language Processing since its creation in 2012, and has developed a broader interest in Machine Learning over the last few years. We tend to foster as much as possible integration of both research topics, for instance by studying training algorithms for large language models.
More specifically, our current research topics include:
- Natural Language Generation / Understanding
- Multilingual text generation
- Controlled text generation (simplification…)
- Low-resource text generation
- Computational narrative understanding
- NLP applications
- Information extraction
- Computer Assisted Language Learning
- Large language models
- Few-shot emotion recognition
- Hybridation of Knowledge Bases and LLMs
- Conversational LLMs
- Machine Learning algorithms
- Enhancement of self-supervised training
- Auxiliary training
- Federated learning