arrow
返回

Modeling relation paths for knowledge base completion via joint adversarial training

delete2020-08-01
delete6
delete
OA
AI
C
Chen Li
X
Xutan Peng
仉
仉尚航 (Shanghang Zhang)
彭
彭浩 (Peng, Hao)
P
Philip S. Yu
何敏 封面图
何敏 (Min He)
L
Linfeng Du
王立红 封面图
王立红 (Lihong Wang) *
DOI:10.1016/j.knosys.2020.105865delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Knowledge Base Completion (KBC), which aims at determining the missing relations between entity pairs, has received increasing attention in recent years. Most existing KBC methods focus on either embedding the Knowledge Base (KB) into a specific semantic space or leveraging the joint probability of Random Walks (RWs) on multi-hop paths. Only a few unified models take both semantic and path-related features into consideration with adequacy. In this paper, we propose a novel method to explore the intrinsic relationship between the single relation (i.e. 1-hop path) and multi-hop paths between paired entities. We use Hierarchical Attention Networks (HANs) to select important relations in multi-hop paths and encode them into low-dimensional vectors. By treating relations and multi-hop paths as two different input sources, we use a feature extractor, which is shared by two downstream components (i.e. relation classifier and source discriminator), to capture shared/similar information between them. By joint adversarial training, we encourage our model to extract features from the multi-hop paths which are representative for relation completion. We apply the trained model (except for the source discriminator) to several large-scale KBs for relation completion. Experimental results show that our method outperforms existing path information-based approaches. Since each sub-module of our model can be well interpreted, our model can be applied to a large number of relation learning tasks. (C) 2020 Elsevier B.V. All rights reserved.
Keyword:
Joint adversarial training
Hierarchical attention mechanism
Knowledge base completion
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

K
Knowledge-Based Systems
IF:
7.6
论文数:
1.3W
被引数:
4.5W

机构

B
Beihang University
学者数:
5.2W
论文数: 4.1W
被引数: 37
C
Carnegie Mellon University
学者数:
1.4W
论文数: 1.4W
被引数: 2.7W
U
University of Illinois Chicago
学者数:
1.7W
论文数: 1.4W
被引数: 3.0W
University of Illinois System 封面图
University of Illinois System
学者数:
6.9W
论文数: 6.2W
被引数: 644
学者 查看更多机构
引用论文

引用论文

Simulation of Underbody Contribution of Wind Noise in a Passenger Automobile
err2013-05-13
err0
PREAI
errRobert Powell; Philippe Moron; Ganapathy Balasubramanian; Barbara Neuhierl; Sivapalan Senthooran; Bernd Crouse; David Freed; Cornelia Kain; Frank Ullrich
err分享
err收藏
Non-operative management of a grade IV pancreatic injury
err2014-04-30
err0
errOAAI
errBharati Hiremath; Nishchit Hegde
err分享
err收藏
学者 查看更多内容