A Hereditary Attentive Template-based Approach for Complex Knowledge Base Question Answering Systems

作者：

Highlights：

• Knowledge base question answering systems struggle to deal with complex questions.

• A template matching approach for complex question answering.

• A Hereditary Attention that inherits the information in a bottom-up way.

• Limitations of datasets for C-KBQA and a new cleaned version of a C-KBQA dataset.

摘要

•Knowledge base question answering systems struggle to deal with complex questions.•A template matching approach for complex question answering.•A Hereditary Attention that inherits the information in a bottom-up way.•Limitations of datasets for C-KBQA and a new cleaned version of a C-KBQA dataset.

论文关键词：Question Answering,Complex Question,Knowledge Base,Semantic Parsing,Neural Networks

论文评审过程：Received 27 October 2021, Revised 12 April 2022, Accepted 31 May 2022, Available online 6 June 2022, Version of Record 14 June 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117725