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

摘要

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 yeso 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.