Abstract
We describe two tutorial dialogue systems that adapt techniques from task-oriented dialogue systems to tutorial dialogue. Both systems employ the same reusable deep natural language understanding and generation components to interpret students' written utterances and to automatically generate adaptive tutorial responses, with separate domain reasoners to provide the necessary knowledge about the correctness of student answers and hinting strategies. We focus on integrating the domain-independent language processing components with domain-specific reasoning and tutorial components in order to improve the dialogue interaction, and present a preliminary analysis of BeeDiff's evaluation.
Original language | English |
---|---|
Title of host publication | SLaTE Workshop on Speech and Language Technology in Education |
Place of Publication | Farmington |
Publisher | Carnegie Mellon University and ISCA Archive |
Pages | 92-95 |
Number of pages | 4 |
Publication status | Published - Oct 2007 |
Event | SLaTE Workshop on Speech and Language Technology in Education - Farmington, Pennsylvania, United States Duration: 1 Oct 2007 → 3 Oct 2007 |
Conference
Conference | SLaTE Workshop on Speech and Language Technology in Education |
---|---|
Country | United States |
City | Farmington, Pennsylvania |
Period | 1/10/07 → 3/10/07 |