My broad interests are in the intersection of computational linguistics and statistical learning. I am most interested in predicting structure from text. Such structure underlies natural language at all its levels, from discourse, through semantics to syntax.

My current interests, all interacting at some level, are: (1) the use of linear algebra for learning statistical models, especially those with hidden variables that are not observed in the data; (2) semantic representations, especially abstract meaning representation and discourse representation structures, and their applications such as document summarization. In my work I use various statistical learning algorithms and language formalisms, including neural networks, spectral methods, probabilistic grammars and others.