Scaling Up Explanation Generation: Large-Scale Knowledge Bases and Empirical Studies

To explain complex phenomena, an explanation system must be able to select information from a formal representation of domain knowledge, organize the selected information into multisentential discourse plans, and realize the discourse plans in text. Although recent years have witnessed signi cant progress in the development of sophisticated computational mechanisms for explanation, empirical results have been limited. This paper reports on a seven year e ort to empirically study explanation generation from semantically rich, large-scale knowledge bases. We rst describe Knight, a robust explanation system that constructs multi-sentential and multi-paragraph explanations from the Biology Knowledge Base, a large-scale knowledge base in the domain of botanical anatomy, physiology, and development. We then introduce the Two Panel evaluation methodology and describe how Knight's performance was assessed with this methodology in the most extensive empirical evaluation conducted on an ex...

• Type: Conference
• Year: 1996
• Where: AAAI
• Authors: James C. Lester, Bruce W. Porter
• Keywords: AAAI 1996, Discourse Plans, Explanation, Intelligent Agents, Large-scale Knowledge Base