Many collective labeling tasks require inference on graphical models where the clique potentials depend only on the number of nodes that get a particular label. We design efficien...
Creating more fine-grained annotated data than previously relevent document sets is important for evaluating individual components in automatic question answering systems. In this...
Social media such as blogs, Facebook, Flickr, etc., presents data in a network format rather than classical IID distribution. To address the interdependency among data instances, ...
This paper presents a novel sequence labeling model based on the latent-variable semiMarkov conditional random fields for jointly extracting argument roles of events from texts. ...
Abstract. Domain adaptation is an important emerging topic in computer vision. In this paper, we present one of the first studies of domain shift in the context of object recogniti...
Kate Saenko, Brian Kulis, Mario Fritz, Trevor Darr...