Expanding, Retrieving and Infilling: Diversifying Cross-Domain Question Generation with Flexible Templates
Expanding, Retrieving and Infilling: Diversifying Cross-Domain Question Generation with Flexible Templates
复制标题
DOI：
10.18653/v1/2021.eacl-main.279
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Xiaojing Yu;Anxiao Jiang
中科院分区：
文献类型：
--
作者：
Xiaojing Yu;Anxiao Jiang
基于序列到序列的模型最近在生成高质量问题方面显示出有希望的结果。然而，这些模型也被称为有主要的缺点，如缺乏多样性和坏的句子结构。在本文中，我们专注于在SQL数据库的问题生成，并提出了一个新的框架，通过扩展，检索和填充，首先结合灵活的模板与基于神经的模型，以生成不同的表达问题的句子结构的指导。此外，针对基于模板的序列到序列生成，提出了一种新的激活/去激活机制，该机制学习区分模板模式和内容模式，从而进一步提高生成质量。我们在两个大规模跨域数据集上进行了实验。实验表明，我们的问题生成方法的优越性，在生产更多样化的问题，同时保持高质量和一致性下的自动评价和人类评价。
Sequence-to-sequence based models have recently shown promising results in generating high-quality questions. However, these models are also known to have main drawbacks such as lack of diversity and bad sentence structures. In this paper, we focus on question generation over SQL database and propose a novel framework by expanding, retrieving, and infilling that first incorporates flexible templates with a neural-based model to generate diverse expressions of questions with sentence structure guidance. Furthermore, a new activation/deactivation mechanism is proposed for template-based sequence-to-sequence generation, which learns to discriminate template patterns and content patterns, thus further improves generation quality. We conduct experiments on two large-scale cross-domain datasets. The experiments show that the superiority of our question generation method in producing more diverse questions while maintaining high quality and consistency under both automatic evaluation and human evaluation.