DOI:
Abstract:
This paper addresses the problem of evaluating students' answers in intelligent tutoring environments with mixed-initiative dialogue by modelling it as a textual entailment problem. The problem of meaning representation and inference is a pervasive challenge in any integrated intelligent system handling communication. For intelligent tutorial dialogue systems, we show that entailment cases can be detected at various dialog turns during a tutoring session. We report the performance of a lexico-syntactic approach on a set of entailment cases that were collected from a previous study we conducted with AutoTutor.