Current textual question answering models achieve strong performance on
in-domain test sets, but often do so by fitting surface-level patterns in the
data, so they fail to generalize to out-of-distribution settings. To make a
more robust and understandable QA system, we model question
本文提出了一个能够改进问题生成中的关键词生成和全局问题语义缺失问题的神经问题生成模型，并且利用了句子级别的语义匹配和答案位置推断功能，并运用了基于答案感知的门控融合机制来增强解码器的初始状态，结果表明我们的模型在 SQuAD 和 MARCO 数据集上领先于现有的最先进模型，同时还对现有模型进行了显著改进。