A Framework for Automatic Question Generation from Text using Deep Reinforcement Learning

Asking intelligent and relevant questions is an important capability of conversational systems such as chatbots. Neural network-based approaches represent the state-of-the-art in automatic question generation (QG). In this work, we attempt to strengthen them significantly by adopting a holistic and novel generator-evaluator framework that directly optimizes objectives that reward semantics and structure. In this paper, we present a novel deep reinforcement learning based framework for automatic question generation. The generator of the framework is a sequence-to-sequence model, whereas the evaluator model of the framework evaluates and assigns a reward to each predicted question. The overall model is trained by learning the parameters of the generator network which maximizes the reward.Our framework allows us to directly optimize any task-specific score including evaluation measures such as BLEU, GLEU, ROUGE-L,etc., suitable for sequence to sequence tasks such as QG. Our evaluation shows that our approach significantly outperforms state-of-the-art systems on the widely-used SQuAD benchmark in both automatic and human evaluation.