François Role

Research Fields

François Role is an associate Professor at Université de Paris Cité, and a member of the Centre Borelli  (UMR 9010). He has worked extensively for several yeras on unsupervised text-mining techniques, knowledge extraction, text clustering and embedding techniques. He has a strong background in NLP ranging from the traditional methods to the most recent generative unimodal and multimodal deep language models.

Publications récentes

• Mira Ait Saada, François Role, Mohamed Nadif. Classification non supervisée de documents à partir des modèles Transformeurs. EGC 2022: 331-338
• Mohamed Nadif, François Role. Unsupervised and self-supervised deep learning approaches for biomedical text mining. Briefings Bioinform. 22(2): 1592-1603 (2021)
• Mira Ait Saada, François Role, Mohamed Nadif. How to Leverage a Multi-layered Transformer Language Model for Text Clustering: an Ensemble Approach. CIKM 2021: 2837-2841
• Mira Ait Saada, François Role, Mohamed Nadif. Unsupervised Methods for the Study of Transformer Embeddings. IDA 2021: 287-300
• François Role, Stanislas Morbieu, Mohamed Nadif. CoClust: A Python Package for Co-Clustering. Journal of Statistical Software 88(7):1-29 (2019)
• François Role, Stanislas Morbieu, Mohamed Nadif. Unsupervised Evaluation of Text Co-clustering Algorithms Using Neural Word Embeddings. CIKM 2018: 1827-1830