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 multi sentential discourse plans and realize the dis course 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 em pirically study explanation generation from se mantically rich large scale knowledge bases We rst describe Knight a robust explana tion 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 physiol ogy 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 explanation system In this evaluation Knight scored within half a grade of domain experts and its performance exceeded that of one of the domain experts