Papers by Shriyash Upadhyay
Learn With Martian: A Tool For Creating Assignments That Can Write And Re-Write Themselves (2023.eacl-demo)
Copied to clipboard
| Challenge: | Using existing course materials, Learn generates questions, selects the best questions, shows them to students, adapts difficulty to student knowledge, and improves as it collects more data on student performance. |
| Approach: | They propose a unified, easy-to-use tool to apply question generation and selection in classrooms. |
| Outcome: | The proposed tool can generate questions, select the best questions, show them to students, adapt difficulty to student knowledge, and improve as it collects more data on student performance. |
A Feasibility Study of Answer-Agnostic Question Generation for Education (2022.findings-acl)
Copied to clipboard
Liam Dugan, Eleni Miltsakaki, Shriyash Upadhyay, Etan Ginsberg, Hannah Gonzalez, DaHyeon Choi, Chuning Yuan, Chris Callison-Burch
| Challenge: | a feasibility study into the applicability of answer-agnostic question generation models to textbook passages is conducted . a significant portion of errors arise from asking irrelevant or un-interpretable questions, a study finds . |
| Approach: | They conduct a feasibility study into the applicability of answer-agnostic question generation models to textbook passages. |
| Outcome: | The proposed model reduces the time it takes to write questions that target salient concepts . the proposed model would help professors write quizzes faster and help students stay engaged . |