Direct relation detection for knowledge-based question answering

作者：

Highlights：

• Direct relation detection using the hierarchical structure of relations.

• Relation detection without using candidate relations.

• Using POS tag of words of questions to compensate for the lack of data.

• One-hot encoding at the character level is used to manage out-of-vocabulary words.

摘要

•Direct relation detection using the hierarchical structure of relations.•Relation detection without using candidate relations.•Using POS tag of words of questions to compensate for the lack of data.•One-hot encoding at the character level is used to manage out-of-vocabulary words.

论文关键词：Question answering,Relation detection,Knowledge base,Natural language processing

论文评审过程：Received 30 December 2021, Revised 14 July 2022, Accepted 22 August 2022, Available online 25 August 2022, Version of Record 5 September 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118678