arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1808.03752cs.CLcs.LG
收藏

基于实体邻居和深层记忆网络的知识图谱嵌入

Knowledge Graph Embedding with Entity Neighbors and Deep Memory Network

Dalian University of Technology(大连理工大学)

Kai Wang, Yu Liu, Xiujuan Xu, Dan Lin

摘要:

知识图谱嵌入是将知识图谱中的实体和关系表示在一个低维的连续向量空间中。近年来的研究主要集中在将结构化知识与附加信息(如实体描述、关系路径等)相结合,但是常用的附加信息往往含有大量的噪声,使得学习有价值的表示变得困难。在本文中,我们提出了一种新的附加信息,称为实体邻居,它包含了给定实体的语义和拓扑特征。然后,我们开发了一个深度记忆网络模型来编码来自邻居的信息。采用门控机制,结构和邻居的表示被集成到一个联合表示。实验结果表明,我们的模型优于现有的KGE方法利用实体描述,并实现了最先进的度量4个数据集。

英文摘要:

Knowledge Graph Embedding (KGE) aims to represent entities and relations of knowledge graph in a low-dimensional continuous vector space. Recent works focus on incorporating structural knowledge with additional information, such as entity descriptions, relation paths and so on. However, common used additional information usually contains plenty of noise, which makes it hard to learn valuable representation. In this paper, we propose a new kind of additional information, called entity neighbors, which contain both semantic and topological features about given entity. We then develop a deep memory network model to encode information from neighbors. Employing a gating mechanism, representations of structure and neighbors are integrated into a joint representation. The experimental results show that our model outperforms existing KGE methods utilizing entity descriptions and achieves state-of-the-art metrics on 4 datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑