Towards Automatic Tutoring of Custom Student-Stated Math Word Problems

Arnau-González, Pablo; Serrano-Mamolar, Ana; Katsigiannis, Stamos; Arevalillo-Herráez, Miguel

Abstract

Math Word Problem (MWP) solving for teaching math with Intelligent Tutoring Systems (ITSs) faces a major limitation: ITSs only supervise pre-registered problems, requiring substantial manual effort to add new ones. ITSs cannot assist with student-generated problems. To address this, we propose an automated approach to translate MWPs to an ITS’s internal representation using pre-trained language models to convert MWP to Python code, which can then be imported easily. Experimental evaluation using various code models demonstrates our approach’s accuracy and potential for improvement.

Citation

Arnau-González, P., Serrano-Mamolar, A., Katsigiannis, S., & Arevalillo-Herráez, M. (2023). Towards Automatic Tutoring of Custom Student-Stated Math Word Problems. In AIED 2023: Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners, Doctoral Consortium and Blue Sky (639-644). https://doi.org/10.1007/978-3-031-36336-8_99

• Conference Name: International Conference on Artificial Intelligence in Education (AIED)
• Conference Location: Tokyo, Japan
• Start Date: Jul 3, 2023
• End Date: Jul 7, 2023
• Acceptance Date: Apr 2, 2023
• Online Publication Date: Jun 30, 2023
• Publication Date: 2023
• Deposit Date: Apr 12, 2023
• Publicly Available Date: Jul 1, 2024
• Publisher: Springer
• Volume: 1831
• Pages: 639-644
• Series Title: Communications in Computer and Information Science
• Book Title: AIED 2023: Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners, Doctoral Consortium and Blue Sky
• DOI: https://doi.org/10.1007/978-3-031-36336-8_99
• Public URL: https://durham-repository.worktribe.com/output/1134170
• Publisher URL: https://link.springer.com/conference/aied