I am assistant professor at the Institute for Logic, Language and Computation (ILLC) at the University of Amsterdam.

My research focuses on probabilistic learning techniques and probabilitistic models for natural language. I am interested in the general problem of learning the syntax and semantics of natural language using "data-driven" methods. This "data" usually consists of large collections of language usage (most commonly, text). In particular, I have worked on "semi-supervised" learning techniques for language, where the data is a combination of bare text, plus text that is annotated with extra syntactic or semantic information. I am also specially interested in the class of grammars called "strongly-lexicalised" grammars. I have worked on semi-supervised learning for such grammars, especially the grammar formalism Combinatory Categorial Grammar (CCG).

I am also interested in the syntax and semantics of my native languages Hindi and Marathi, and have worked on building CCG parsers and resources for Hindi.