890 search results - page 80 / 178 » Learning a Generative Model for Structural Representations |
ANLP
2000
13 years 10 months ago
2000
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...
ICASSP
2011
IEEE
13 years 20 days ago
2011
IEEE
This paper considers application of Deep Belief Nets (DBNs) to natural language call routing. DBNs have been successfully applied to a number of tasks, including image, audio and ...
EXACT
2007
13 years 11 months ago
2007
In order to assist a power plant operator to face unusual situations, we have developed an intelligent assistant that explains the suggested commands generated by an MDP-based pla...
JMLR
2008
13 years 9 months ago
2008
In supervised learning, a training set consisting of labeled instances is used by a learning algorithm for generating a model (classifier) that is subsequently employed for decidi...
CVPR
2008
IEEE
14 years 11 months ago
2008
IEEE
An important problem in image labeling concerns learning with images labeled at varying levels of specificity. We propose an approach that can incorporate images with labels drawn...