计算机科学
人工智能
图形
卷积神经网络
理论计算机科学
知识图
深度学习
机器学习
人工神经网络
作者
Xueting Wang,Fang Miao,Libiao Jin
出处
期刊:2020 International Conference on Culture-oriented Science & Technology (ICCST)
日期:2020-10-01
标识
DOI:10.1109/iccst50977.2020.00047
摘要
Knowledge Graph Completion (KGC) aims to find the missing relationships between entities. In this paper, we introduce a novel embedding method based on Convolutional Neural Networks (CNNs) for KGC task. Different from the existing model ConvKB, we design three different shapes of filters to produce more useful features, rather than extracting the features by the filters with the same shape of 1 × 3. Experiments show that our model obtains better link prediction results than the previous models on two benchmark datasets WN18RR and FB15k-237.
科研通智能强力驱动
Strongly Powered by AbleSci AI