Automatically Generating Cause-and-Effect Questions from Passages

Katherine Stasaski, Manav Rathod, Tony Tu, Yunfang Xiao, Marti A. Hearst


Abstract
Automated question generation has the potential to greatly aid in education applications, such as online study aids to check understanding of readings. The state-of-the-art in neural question generation has advanced greatly, due in part to the availability of large datasets of question-answer pairs. However, the questions generated are often surface-level and not challenging for a human to answer. To develop more challenging questions, we propose the novel task of cause-and-effect question generation. We build a pipeline that extracts causal relations from passages of input text, and feeds these as input to a state-of-the-art neural question generator. The extractor is based on prior work that classifies causal relations by linguistic category (Cao et al., 2016; Altenberg, 1984). This work results in a new, publicly available collection of cause-and-effect questions. We evaluate via both automatic and manual metrics and find performance improves for both question generation and question answering when we utilize a small auxiliary data source of cause-and-effect questions for fine-tuning. Our approach can be easily applied to generate cause-and-effect questions from other text collections and educational material, allowing for adaptable large-scale generation of cause-and-effect questions.
Anthology ID:
2021.bea-1.17
Volume:
Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications
Month:
April
Year:
2021
Address:
Online
Venue:
BEA
SIG:
SIGEDU
Publisher:
Association for Computational Linguistics
Note:
Pages:
158–170
Language:
URL:
https://aclanthology.org/2021.bea-1.17
DOI:
Bibkey:
Cite (ACL):
Katherine Stasaski, Manav Rathod, Tony Tu, Yunfang Xiao, and Marti A. Hearst. 2021. Automatically Generating Cause-and-Effect Questions from Passages. In Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications, pages 158–170, Online. Association for Computational Linguistics.
Cite (Informal):
Automatically Generating Cause-and-Effect Questions from Passages (Stasaski et al., BEA 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.bea-1.17.pdf
Optional supplementary material:
 2021.bea-1.17.OptionalSupplementaryMaterial.zip
Code
 kstats/causalqg
Data
HotpotQANewsQASQuADTQA