Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                

Enhancing Human Summaries for Question-Answer Generation in Education

Hannah Gonzalez, Liam Dugan, Eleni Miltsakaki, Zhiqi Cui, Jiaxuan Ren, Bryan Li, Shriyash Upadhyay, Etan Ginsberg, Chris Callison-Burch


Abstract
We address the problem of generating high-quality question-answer pairs for educational materials. Previous work on this problem showed that using summaries as input improves the quality of question generation (QG) over original textbook text and that human-written summaries result in higher quality QG than automatic summaries. In this paper, a) we show that advances in Large Language Models (LLMs) are not yet sufficient to generate quality summaries for QG and b) we introduce a new methodology for enhancing bullet point student notes into fully fledged summaries and find that our methodology yields higher quality QG. We conducted a large-scale human annotation study of generated question-answer pairs for the evaluation of our methodology. In order to aid in future research, we release a new dataset of 9.2K human annotations of generated questions.
Anthology ID:
2023.bea-1.9
Volume:
Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Ekaterina Kochmar, Jill Burstein, Andrea Horbach, Ronja Laarmann-Quante, Nitin Madnani, Anaïs Tack, Victoria Yaneva, Zheng Yuan, Torsten Zesch
Venue:
BEA
SIG:
SIGEDU
Publisher:
Association for Computational Linguistics
Note:
Pages:
108–118
Language:
URL:
https://aclanthology.org/2023.bea-1.9
DOI:
10.18653/v1/2023.bea-1.9
Bibkey:
Cite (ACL):
Hannah Gonzalez, Liam Dugan, Eleni Miltsakaki, Zhiqi Cui, Jiaxuan Ren, Bryan Li, Shriyash Upadhyay, Etan Ginsberg, and Chris Callison-Burch. 2023. Enhancing Human Summaries for Question-Answer Generation in Education. In Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023), pages 108–118, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Enhancing Human Summaries for Question-Answer Generation in Education (Gonzalez et al., BEA 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.bea-1.9.pdf
Attachment:
 2023.bea-1.9.attachment.zip
Video:
 https://aclanthology.org/2023.bea-1.9.mp4