.png){kind=icon}
返回
Novel translation knowledge graph completion model based on 2D convolution
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-021-02438-8.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The knowledge graph completion task involves predicting missing entities and relations in a knowledge graph. Many models have achieved good results, but they have become increasingly complex. In this study, we propose a simple translation-based model that relies on the fact that the multiplication of subjects and relations is approximately equal to the object. First, we utilize embeddings to represent entities and relations. Second, we perform vector multiplication on subject embedding and relation embedding to generate a 2D matrix and achieve full fusion of embedding at the element level. Third, we adopt a convolutional neural network on the 2D matrix. Thereafter, we can generate feature maps, which are then spliced into a 1D feature vector. The feature vector is transformed into predicted object embedding through a fully connected operation. Finally, we use the scoring function to score the candidate triples. Experimental results strongly demonstrate that the translation knowledge graph completion model based on 2D convolution achieves state-of-the-art results compared with the baseline.
Keyword:
Knowledge graph completion
Convolutional neural network
Translation model
Entity relation matrix
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
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
引用论文
Ligand substitution reactions of metal and organometal carbonyls with group V and VI donor ligands
.png){kind=icon}
PREAI
分享收藏
分享收藏Comparison of linear and planar arrays for auroral clutter control in an over-the-horizon radar线性与平面阵列在超视距雷达极光杂波控制中的比较
PREAI
分享收藏
查看更多内容