Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring
Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring
复制标题
DOI：
10.1609/aaai.v34i05.6366
复制
发表时间：
2019-12
期刊：
影响因子：
--
通讯作者：
Xiyao Ma;Qile Zhu;Yanlin Zhou;Xiaolin Li;D. Wu
中科院分区：
文献类型：
--
作者：
Xiyao Ma;Qile Zhu;Yanlin Zhou;Xiaolin Li;D. Wu
以答案及其上下文作为输入，序列到序列模型在问题生成方面取得了相当大的进展。然而，我们观察到，这些方法经常生成错误的问题词或关键字，并从输入中复制与答案无关的词。我们认为缺乏全局问题语义和没有很好地利用答案位置意识是关键的根本原因。在本文中，我们提出了一个神经问题生成模型，包括两个通用模块：文本级语义匹配和答案位置推断。此外，我们通过利用答案感知门控融合机制来增强解码器的初始状态。实验结果表明，我们的模型优于最先进的（SOTA）模型SQuAD和MARCO数据集。由于其通用性，我们的工作也显着改善现有的模型。
Taking an answer and its context as input, sequence-to-sequence models have made considerable progress on question generation. However, we observe that these approaches often generate wrong question words or keywords and copy answer-irrelevant words from the input. We believe that lacking global question semantics and exploiting answer position-awareness not well are the key root causes. In this paper, we propose a neural question generation model with two general modules: sentence-level semantic matching and answer position inferring. Further, we enhance the initial state of the decoder by leveraging the answer-aware gated fusion mechanism. Experimental results demonstrate that our model outperforms the state-of-the-art (SOTA) models on SQuAD and MARCO datasets. Owing to its generality, our work also improves the existing models significantly.