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.
Anthology ID:
2020.bea-1.19
Volume:
Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications
Month:
July
Year:
2020
Address:
Seattle, WA, USA → Online
Editors:
Jill Burstein, Ekaterina Kochmar, Claudia Leacock, Nitin Madnani, Ildikó Pilán, Helen Yannakoudakis, Torsten Zesch
Venue:
BEA
SIG:
SIGEDU
Publisher:
Association for Computational Linguistics
Note:
Pages:
186–192
Language:
URL:
https://aclanthology.org/2020.bea-1.19
DOI:
10.18653/v1/2020.bea-1.19
Bibkey:
Cite (ACL):
Aoife Cahill, James H Fife, Brian Riordan, Avijit Vajpayee, and Dmytro Galochkin. 2020. Context-based Automated Scoring of Complex Mathematical Responses. In Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 186–192, Seattle, WA, USA → Online. Association for Computational Linguistics.
Cite (Informal):
Context-based Automated Scoring of Complex Mathematical Responses (Cahill et al., BEA 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.bea-1.19.pdf