Educational Multi-Question Generation for Reading Comprehension

Manav Rathod, Tony Tu, Katherine Stasaski


Abstract
Automated question generation has made great advances with the help of large NLP generation models. However, typically only one question is generated for each intended answer. We propose a new task, Multi-Question Generation, aimed at generating multiple semantically similar but lexically diverse questions assessing the same concept. We develop an evaluation framework based on desirable qualities of the resulting questions. Results comparing multiple question generation approaches in the two-question generation condition show a trade-off between question answerability and lexical diversity between the two questions. We also report preliminary results from sampling multiple questions from our model, to explore generating more than two questions. Our task can be used to further explore the educational impact of showing multiple distinct question wordings to students.
Anthology ID:
2022.bea-1.26
Volume:
Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)
Month:
July
Year:
2022
Address:
Seattle, Washington
Venue:
BEA
SIG:
SIGEDU
Publisher:
Association for Computational Linguistics
Note:
Pages:
216–223
Language:
URL:
https://aclanthology.org/2022.bea-1.26
DOI:
10.18653/v1/2022.bea-1.26
Bibkey:
Cite (ACL):
Manav Rathod, Tony Tu, and Katherine Stasaski. 2022. Educational Multi-Question Generation for Reading Comprehension. In Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022), pages 216–223, Seattle, Washington. Association for Computational Linguistics.
Cite (Informal):
Educational Multi-Question Generation for Reading Comprehension (Rathod et al., BEA 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.bea-1.26.pdf
Video:
 https://preview.aclanthology.org/ingestion-script-update/2022.bea-1.26.mp4
Code
 kstats/multiquestiongeneration
Data
SQuAD