by Cristina Conati (based on joint work with Giuseppe Carenini)
I will present a framework that helps students learn from examples by generating example problem solutions whose level of detail is tailored to the students' domain knowledge. I will describe how each new example is created by using a probabilistic user model and natural language generation techniques to selectively introduce gaps in the example solution. The goal is to generate examples that allow a student to practice applying rules learned from previous examples in problem solving episodes of difficulty adequate to her knowledge.