Context-based Automated Scoring of Complex Mathematical Responses

Aoife Cahill, James H. Fife, Brian Riordan, Avijit Vajpayee, Dmytro Galochkin

Abstract: The tasks of automatically scoring either textual or algebraic responses to mathematical questions have both been well-studied, albeit separately. In this paper we propose a method for automatically scoring responses that contain both text and algebraic expressions. Our method not only achieves high agreement with human raters, but also links explicitly to the scoring rubric – essentially providing explainable models and a way to potentially provide feedback to students in the future.