A Semantic Role-based Approach to Open-Domain Automatic Question Generation

Michael Flor, Brian Riordan


Abstract
We present a novel rule-based system for automatic generation of factual questions from sentences, using semantic role labeling (SRL) as the main form of text analysis. The system is capable of generating both wh-questions and yes/no questions from the same semantic analysis. We present an extensive evaluation of the system and compare it to a recent neural network architecture for question generation. The SRL-based system outperforms the neural system in both average quality and variety of generated questions.
Anthology ID:
W18-0530
Volume:
Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Venues:
BEA | NAACL | WS
SIG:
SIGEDU
Publisher:
Association for Computational Linguistics
Note:
Pages:
254–263
Language:
URL:
https://aclanthology.org/W18-0530
DOI:
10.18653/v1/W18-0530
Bibkey:
Cite (ACL):
Michael Flor and Brian Riordan. 2018. A Semantic Role-based Approach to Open-Domain Automatic Question Generation. In Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 254–263, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
A Semantic Role-based Approach to Open-Domain Automatic Question Generation (Flor & Riordan, 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-0530.pdf
Data
SQuAD