Expert Tutoring and Natural Language Feedback in Intelligent Tutoring Systems

Intelligent tutoring systems can provide benefits of one-on-one instruction automatically and cost effectively. To make the intelligent tutoring systems as effective as expert human tutors, my research aims at investigating what type of natural language feedback an intelligent tutoring system should provide and how to implement the feedback generation to engender significantly more learning than simple practice. This paper describes a comprehensive study of expert versus non-expert tutoring and a baseline intelligent tutoring system which provides different kinds of feedback. It then proposes a method to computationally model expert tutoring and a framework of effective natural language feedback generation with 3-tier probabilistic planning.