Reinforcement learning-driven deep question generation with rich semantics

Menghong Guan, Subrota Kumar Mondal, Hong-Ning Dai, Haiyong Bao

Abstract: Highlights•Integrating reinforcement learning and semantic information methods for deep question generation.•Using multiple evaluation metrics: naturality, relevance, answerability, and difficulty in reward system.•Extensive experiments demonstrate the proposed method achieving state-of-the-art performance.