Affiliation:
1. Florida Institute for Human and Machine Cognition, USA
2. University of Rochester, USA
Abstract
This chapter describes a dialog system for task learning and its application to textual user interfaces. Our system, PLOW, uses observation of user demonstration, together with the user’s play-by-play description of that demonstration, to learn complex tasks. We describe some preliminary experiments which show that this technique may make it possible for users without any programming experience to create tasks via natural language.
Reference14 articles.
1. Allen, J., Blaylock, N., & Ferguson, G. (2002). A problem solving model for collaborative agents. Proceedings of the International Joint Conference on Autonomous Agents and Multi-Agent Systems.
2. An architecture for a generic dialogue shell
3. Angros, R., Jr., Johnson, W. L., Rickel, J., & Scholer, A. (2002). Learning domain knowledge for teaching procedural skills. In Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems.
4. Chambers, N., Allen, J., Galescu, L., Jung, H., & Taysom, W. (2006). Using semantics to identify web objects. In Proceedings of the Twenty-First National Conference on Artificial Intelligence (AAAI-06).
5. Linking Semantic and Knowledge Representations in a Multi-Domain Dialogue System