Trude Heift & Paul McFetridge

E-Mail: {heift, mcfet} @sfu.ca

Whereas Student Models typically are used for cognitive diagnosis and/or to represent behavioural and conceptual knowledge of the student, a Student Model in an Intelligent Language Tutoring System (ILTS) can also assist in the analysis of students' input. One of the typical problems of Natural Language Processing (NLP) is the explosive property of the parser and this is aggravated in an Intelligent Language Tutor because the grammar is unconstrained and generates even more parses. In the system described here several modules are responsible for selecting the appropriate analysis and these are informed by the Student Model and other factors. Aspects in the Student Model such as the performance history of the student play an important role in determining the desired sentence interpretation, handling multiple errors, and deciding on the level of interaction with the student.