photo Logo LIF Logo UMA

My Research

I did my PhD on the learning of context-free languages, from positive or positive and negative non-structured examples. This work is known as the starting point of what is now called Distributional Learning (Alexander Clark is clearly better than me to explain the main ideas). When I arrived in Marseille, I continued this kind of work, but my interest grew also into more common machine learning approaches. The proximity of a bunch of brilliant and friendly researchers interested in statistical machine learning, natural languages processing, or multi-media indexing and retrieval, created an exiting environment. Though I still feel like a theoretician, this is certainly the reason why I become interested into more practical algorithms, for NLP or user mining for instance. I have recently started to work on graph grammar learning, with the aim to apply it to concept detection in images.
During my stay in the US, I also started working on learning subsequential transducers for phonology purpose, and I liked it!
My main research topics are:


Page under construction