Paper: Leveraging Hidden Dialogue State to Select Tutorial Moves

ACL ID W10-1009
Title Leveraging Hidden Dialogue State to Select Tutorial Moves
Venue Innovative Use of NLP for Building Educational Applications
Year 2010

A central chalenge for tutorial dialogue systems is selecting an apropriate move given the dialogue context. Corpus-based aproaches to creating tutorial dialogue management models may facilitate more flexible and rapid development of tutorial dialogue systems and may increase the efectivenes of these systems by alowing data-driven adaptation to learning contexts and to individual learners. This paper presents a family of models, including first-order Markov, hiden Markov, and hierarchical hiden Markov models, for predicting tutor dialogue acts within a corpus. This work takes a step toward fuly data-driven tutorial dialogue management models, and the results highlight important directions for future work in unsupervised dialogue modeling.