Bastien Liétard

bastien [dot] lietard [at] inria [dot] fr

French PhD student at INRIA MAGNET, affiliated with University of Lille.

My PhD is about studying (lexical) semantic change dynamics using statistical learning models for different languages (particularly French and English). This work is supervised by Marc Tommasi, Pascal Denis and Mikaela Keller (INRIA MAGNET team) and Anne Carlier (STIH unit, Paris Sorbonne University)

Current research interests: Semantics, Pragmatics, Historical Linguistics, Statistics and Machine Learning.

Past notable works

During the second year of my M.Sc, I worked on the same topic as my PhD with Pascal Denis and Mikaela Keller (INRIA MAGNET team). It allowed me to discover the state-of-the-art earlier and we focused on lexical semantic change in synonymous pairs of words.

In 2021 I did a research intership in the CoAStAL group at the University of Copenhagen, under the supervision of Anders Søgaard. My reseach was about probing Language Models for geographic knowledge (see the paper).

During my B.Sc and my first year of Master, I worked on Language Modeling and Semantics of adjectives, with a focus on so-called privative adjectives. This could be ranged under a specific type of adjective-noun compositionality.

Outside of research

I am writing tabletop RPGs (both game design and narrative design) and my own novel - at a disastrous pace.

I am generally interested in fantasy and sci-fi (especially cyberpunk) cultures, poetry, and 13th century european history.

I can also provide a lot of music recommendations, if I'm asked to.


Master of Data Science

University of Lille, Centrale Lille and IMT Lille-Douai
Second year thesis : "Methods for modeling Lexical Semantic Change and linguistic perspectives".
First year thesis : "Studying semantics of adjectives with neural Language Models".

High Honors


Bachelor of Applied Mathematics and Computer Science to Social Sciences and Humanities, spec. Linguistics

University of Lille
Final dissertation : "Uses of LSTM neural networks in NLP".

Highest Honors