Gervasio, M. and Yeh, E. and Myers, K. Learning to Ask the Right Questions, in Proceedings of the AAMAS Workshop on Agents Learning Interactively from Human Teachers , 2010.
Abstract
Asking questions is an integral part of learning. Asking questions can clarify concepts, test hypotheses, add missing information, or provide additional knowledge to facilitate learning. The last item motivates the work described in this paper. By asking questions, our system obtains information that serves as background knowledge for a base learner, enabling the base learner to make useful generalizations even with few training examples. In previous work, we developed static strategies for question asking. Here, we extend that work with a learning approach for acquiring question-asking strategies that better accommodates the interdependent nature of questions. We present experiments validating the approach and showing its usefulness for acquiring efficient, context-dependent question-asking strategies.
Keywords: Active learning, decision tree induction, metalearning, preference learning