期刊
NEUROCOMPUTING
卷 515, 期 -, 页码 37-47出版社
ELSEVIER
DOI: 10.1016/j.neucom.2022.10.023
关键词
Knowledge base question answering; Dynamic subgraph reasoning; Enhance intermediate supervision signals
This paper proposes a method of dynamically expanding subgraphs for multi-hop knowledge base question answering. By connecting different subgraphs at each step and generating strong intermediate signals, the method is able to obtain the correct answer.
Knowledge base question answering aims to answer a question over a knowledge base. Multi-hop knowledge base question answering is a challenging task because it requires multi-step reasoning according to the question to get the answer. Existing models infer the answer over a static subgraph or attend to different parts of the question through an intermediate signal. The former obtains limited semantic information, and the latter provides limited reasoning due to the weak supervision signal. In this paper, we eliminate the limitation of static subgraph reasoning by dynamically expanding subgraphs, which connect the question and subgraph to form a joint subgraph. We then adjust the dynamic subgraph to enable reasoning at each step. Specifically, at each step, the question connects different subgraphs, respects the context while paying attention to a specific part of the question, generates a strong intermediate signal, acts on the subsequent reasoning, and finally obtains a correct answer. A large number of experiments on three datasets show that our method performs better than previous state-of-the-art models. (C) 2022 Published by Elsevier B.V.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据