A framework for automatic question generation from text using deep reinforcement learning
share
Automatic question generation (QG) is a useful yet challenging task in NLP. Recent neural network-based approaches represent the state-of-the-art in this task, but they are not without shortcomings. Firstly, these models lack the ability to handle rare words and the word repetition problem. Moreover, all previous works optimize the cross-entropy loss, which can induce inconsistencies between training (objective) and testing (evaluation measure). 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, enhanced with the copy mechanism to handle the rare-words problem and the coverage mechanism to solve the word repetition problem. 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 comprehensive evaluation shows that our approach significantly outperforms state-of-the-art systems on the widely-used SQuAD benchmark in both automatic and human evaluation.
READ FULL TEXT