ARL: An adaptive reinforcement learning framework for complex question answering over knowledge base

作者：

Highlights：

• We propose a new adaptive reinforcement learning (ARL) framework to adaptively extend the relation paths.

• We propose a semantic policy network to choose the optimal actions.

• We introduce a new reward function, with the aim of alleviating the issue of delayed and sparse rewards.

摘要

•We propose a new adaptive reinforcement learning (ARL) framework to adaptively extend the relation paths.•We propose a semantic policy network to choose the optimal actions.•We introduce a new reward function, with the aim of alleviating the issue of delayed and sparse rewards.

论文关键词：Question answering,Knowledge base,Text mining,Reinforcement learning

论文评审过程：Received 20 November 2021, Revised 11 March 2022, Accepted 20 March 2022, Available online 5 April 2022, Version of Record 5 April 2022.

论文官网地址：https://doi.org/10.1016/j.ipm.2022.102933