Describing images with sentences
We have collected a data set of images annotated with several sentences that
describe each image. Can we use these captions to automatically infer what is
in the image? Can we learn to associate images with their captions?
Combinatory Categorial Grammar parsing
Combinatory Categorial Grammar (CCG) is a linguistically expressive grammar
formalism with a transparent interface between syntactic structures and
semantic interpretations.
Our research group focuses on Natural Language Processing. We are particularly
interested in the use of linguistically expressive, yet computationally
tractable grammars for wide-coverage parsing and other applications. We are also interested in the interface between natural language and vision.