about me

I am a tenured Research Scientist with INRIA, the French National Institute for Research in Computer Science and Control. My current affiliation is with the Mostrare project-team, a joint research group between INRIA Nord Lille Europe Research Center and University of Lille Computer Science Department (LIFL).

Before moving to INRIA, I worked as a Natural Language Scientist for Powerset Inc. (now part of Microsoft, Inc.), a San Francisco-based company specialized in the application of NLP techniques to web search. Before that, I studied at the University of Texas at Austin, from which I received a PhD in 2007. Earlier on, I studied at Université Libre de Bruxelles, Université de Toulouse, and University of Edinbugh.

My main specialization is in computational linguistics and my primary research interests are in formal and computational models of syntax, semantics, and discourse. Over the recent years, I have become very interested in Machine Learning, and especially in applying ML techniques to NLP problems. My dissertation investigates various learning-based models for anaphora and coreference resolution. Most of my publications, including my dissertation, can be found here. Most of the research projects, software and resources that I have contributed to are listed here. For more information, see my CV.