We present three approaches for unsupervised grammar induction that are sensitive to data complexity and apply them to Klein and Manning's Dependency Model with Valence. The ...
Valentin I. Spitkovsky, Hiyan Alshawi, Daniel Jura...
In recent years there have been efforts to develop a probabilistic framework to explain the workings of a Learning Classifier System. This direction of research has met with lim...
Relation extraction, the process of converting natural language text into structured knowledge, is increasingly important. Most successful techniques use supervised machine learni...
The Ringling School of Art and Design is a fully accredited four year college of visual art and design with a student population of approximately 1000. The Ringling School has ach...
We present a unified framework for reasoning about worst-case regret bounds for learning algorithms. This framework is based on the theory of duality of convex functions. It brin...