My broad interests are in the intersection of computational linguistics and machine learning. I am interested in developing ways for reasoning about compositional structures such as parse trees through the use of formalisms such as probabilistic grammars.

Much of my research has relied on capturing the syntax of natural language using probabilistic grammars -- grammars which originate in linguistics and formal language theory, and which have been augmented with a probabilistic interpretation. I have worked with various grammars, such as probabilistic context-free grammars (PCFGs), latent-variable PCFGs, dependency grammars, adaptor grammars, tree substitution grammars, shift-reduce grammars and others.