Natural Language Generation for Intelligent Tutoring Systems: a case study

To investigate whether Natural Language feedback improves learning, we developed two different feedback generation engines, that we systematically evaluated in a three way comparison that included the original system as well. We found that the system which intuitively produces the best language does engender the most learning. Specifically, it appears that presenting feedback at a more level is responsible for the improvement. Keywords. Intelligent Tutoring Systems. Feedback Generation.

• Type: Conference
• Year: 2005
• Where: AIED
• Authors: Barbara Di Eugenio, Davide Fossati, Dan Yu, Susan M. Haller, Michael Glass
• Keywords: AIED 2005, Artificial Intelligence, Feedback Generation, Intelligent Tutoring Systems, Natural Language Feedback