Natural Question Generation with Reinforcement Learning Based Graph-to-Sequence Model
This work addresses question generation for educational or QA systems, showing incremental improvements with a novel hybrid approach.
The paper tackles natural question generation from passages and answers by proposing a reinforcement learning-based graph-to-sequence model, which outperforms previous state-of-the-art methods by a large margin on the SQuAD dataset.
Natural question generation (QG) aims to generate questions from a passage and an answer. In this paper, we propose a novel reinforcement learning (RL) based graph-to-sequence (Graph2Seq) model for QG. Our model consists of a Graph2Seq generator where a novel Bidirectional Gated Graph Neural Network is proposed to embed the passage, and a hybrid evaluator with a mixed objective combining both cross-entropy and RL losses to ensure the generation of syntactically and semantically valid text. The proposed model outperforms previous state-of-the-art methods by a large margin on the SQuAD dataset.