From recording linguistic competence to supporting inferences about language acquisition in context

Abstract

Student models for Intelligent Computer Assisted Language Learning (ICALL) have largely focused on the acquisition of grammatical structures. In this paper, we motivate a broader perspective of student models for ICALL that incorporates insights from current research on second language acquisition and language testing. We argue for a student model that includes a representation of the learner's ability to use language in context and to perform tasks, as well as for an explicit activity model that provides information on the language tasks and the inferences for the student model they support. The student model architecture we present is being developed as part of the TAGARELA system, an intelligent workbook supporting the instruction of Portuguese.

Keywords:

• Intelligent Computer-Assisted Language Learning (ICALL)
• intelligent tutoring systems (ITS)
• natural language processing (NLP)
• second language acquisition (SLA)
• student model
• learner model
• activity model
• task appropriateness
• task strategies
• L1 transfer

Acknowledgements

For helpful discussion and suggestions, we would like to thank the ICALL research group (http://purl.org/net/icall) at the Ohio State University, where we developed the work reported here: Susan Bull, Trude Heift, Donna Long, Kathy McCoy, Bob Mislevy, Scott Payne, Mathias Schulze and the reviewers of UserModeling 2007, where an earlier version of our proposal was presented (Amaral & Meurers, 2007a).

Notes

1. This simplification was necessary at this stage of the project development for purely practical reasons.

2. For expository reasons, this example uses the inverse scenario of TAGARELA, which is used by Americans learning Portuguese.