当前位置: X-MOL 学术IEEE Access › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
3DRTE: 3D Rotation Embedding in Temporal Knowledge Graph
IEEE Access ( IF 3.4 ) Pub Date : 2020-01-01 , DOI: 10.1109/access.2020.3036897
Jingbin Wang , Wang Zhang , Xinyuan Chen , Jing Lei , Xiaolian Lai

Temporal knowledge graph (TKG) embedding has received increasing attention in the academia. However, most existing methods are extensions of traditional translation models. Due to their intrinsic limitations, it is often difficult for such methods to effectively model essential characteristics of TKG, namely three basic relation patterns including symmetry/antisymmetry, inversion, and composition. In this paper, a new 3-Dimensional Rotation Temporal Embedding (3DRTE) method is proposed. Firstly, we selectively fuse temporal and relational features of fact triples by taking advantages of self-attention mechanism in processing sequential information. Then, entities are modelled as points in three-dimensional space, and the relations are interpreted as two isoclinic rotations between entities with Quaternion. Experimental results on several public datasets show that our method obtains state-of-the-art results.

中文翻译:

3DRTE:时间知识图谱中的 3D 旋转嵌入

时间知识图(TKG)嵌入在学术界受到越来越多的关注。然而,大多数现有方法是传统翻译模型的扩展。由于其固有的局限性,这些方法通常很难有效地对 TKG 的基本特征进行建模,即对称/反对称、反演和合成三种基本关系模式。在本文中,提出了一种新的3维旋转时间嵌入(3DRTE)方法。首先,我们利用自注意力机制在处理序列信息时有选择地融合事实三元组的时间和关系特征。然后,实体被建模为三维空间中的点,关系被解释为具有四元数的实体之间的两个等斜旋转。
更新日期:2020-01-01
down
wechat
bug