About me
I am a “Maître de conférences” (associate professor, more or less) at Université Sorbonne Nouvelle in the department of ILPGA and Lattice laboratory.
I got a bachelor’s degree in computer science at Université d’Orléans in 2010 and a master degree at Université d’Orléans in 2012. Then I went on a PhD CIFRE at Université Sorbonne Nouvelle Paris 3 in partnership with the company Expert System France (ex TEMIS). My PhD was supervised by Isabelle Tellier along with my co-tutors Christian Lautier and Marco Dinarelli. I am now a PhD in NLP.
Curriculum Vitae: English (one day…) | French
Research Interests
My current research focuses on estimating stereotypical biases in language models and the application of NLP methods to lower resourced languages.
My research also revolve around named entities, from their recognition in the text to the extraction of the relationships they share with each other. For those tasks, I mainly use machine learning, especially CRFs and neural networks.
My researches lead me to take an interest in the annotation process, how to create and evaluate annotated corpora. For this tasks, I am heading towards active learning.
I am the main developer of Segmenteur étiqueteur makovien (SEM), a tool for syntactic annotations relying on machine learning.
My PhD Thesis
Informations about my thesis are available here. It is available (in French) on TEL archives.
Free, open source projects
- Python Autonomous Lafon specificity Scripts (PALS) : dependency-less scripts for computing Lafon specificity (a measure based on the hypergeometric distribution) on text corpora.
- Segmenteur étiqueteur makovien (SEM) : segmentation and annotation of French textual data (PoS, chunking, NER).