Paper: Understanding Complex Natural Language Explanations In Tutorial Applications

ACL ID W06-3503
Title Understanding Complex Natural Language Explanations In Tutorial Applications
Venue Workshop On Scalable Natural Language Understanding
Session
Year 2006
Authors

We describe the WHY2-ATLAS intelligent tutoring system for qualitative physics that interacts with students via natural lan- guage dialogue. We focus on the is- sue of analyzing and responding to multi- sentential explanations. We explore an ap- proach that combines a statistical classi- fier, multiple semantic parsers and a for- mal reasoner for achieving a deeper under- standing of these explanations in order to provide appropriate feedback on them.