When learning a classical instrument, people often either take lessons in which an existing body of “technique” is delivered, evolved over generations of performers, or in som...
Active learning methods seek to reduce the number of labeled examples needed to train an effective classifier, and have natural appeal in spam filtering applications where trustwo...
Multi-label learning deals with ambiguous examples each may belong to several concept classes simultaneously. In this learning framework, the inherent ambiguity of each example is...
Reinforcement learning is an effective machine learning paradigm in domains represented by compact and discrete state-action spaces. In high-dimensional and continuous domains, ti...
This paper describes a novel method by which a dialogue agent can learn to choose an optimal dialogue strategy. While it is widely agreed that dialogue strategies should be formul...
Marilyn A. Walker, Jeanne Frommer, Shrikanth Naray...