Personalized information agents can help overcome some of the limitations of communal Web information sources such as portals and search engines. Two important components of these...
We develop a semi-supervised learning method that constrains the posterior distribution of latent variables under a generative model to satisfy a rich set of feature expectation c...
In this paper we present an implemented account of multilingual linguistic resources for multilingual text generation that improves significantly on the degree of re-use of resour...
John A. Bateman, Christian Matthiessen, Licheng Ze...
We show how a preselection of hidden variables can be used to efficiently train generative models with binary hidden variables. The approach is based on Expectation Maximization (...
We consider the problem of multi-label, supervised image segmentation when an initial labeling of some pixels is given. In this paper, we propose a new generative image segmentatio...
Tae Hoon Kim (Seoul National University), Kyoung M...