We present three systems for surface natural language generation that are trainable from annotated corpora. The first two systems, called NLG1 and NLG2, require a corpus marked on...
We formulate a principle for classification with the knowledge of the marginal distribution over the data points (unlabeled data). The principle is cast in terms of Tikhonov styl...
We address the problem of visually detecting causal events and tting them together into a coherent story of the action witnessed by the camera. We show that this can be done by re...
The creation of a complex web site is a thorny problem in user interface design. First, di erent visitors have distinct goals. Second, even a single visitor may have di erent need...
We propose a new approach to the problem of searching a space of policies for a Markov decision process (MDP) or a partially observable Markov decision process (POMDP), given a mo...