Improving multi-hop knowledge base question answering by learning intermediate supervision signals

作     者：He, Gaole Lan, Yunshi Jiang, Jing Zhao, Wayne Xin Wen, Ji-Rong 

作者机构：School of Information Renmin University of China China School of Information System Singapore Management University Singapore Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2021年

核心收录：

主　　题：Knowledge based systems 

摘      要：Multi-hop Knowledge Base Question Answering (KBQA) aims to find the answer entities that are multiple hops away in the Knowledge Base (KB) from the entities in the question. A major challenge is the lack of supervision signals at intermediate steps. Therefore, multi-hop KBQA algorithms can only receive the feedback from the final answer, which makes the learning unstable or ineffective. To address this challenge, we propose a novel teacher-student approach for the multi-hop KBQA task. In our approach, the student network aims to find the correct answer to the query, while the teacher network tries to learn intermediate supervision signals for improving the reasoning capacity of the student network. The major novelty lies in the design of the teacher network, where we utilize both forward and backward reasoning to enhance the learning of intermediate entity distributions. By considering bidirectional reasoning, the teacher network can produce more reliable intermediate supervision signals, which can alleviate the issue of spurious reasoning. Extensive experiments on three benchmark datasets have demonstrated the effectiveness of our approach on the KBQA task. The code to reproduce our analysis is available at https://***/RichardHGL/WSDM2021_NSM. Copyright © 2021, The Authors. All rights reserved.