Learning Description-Based Representations for Temporal Knowledge Graph Reasoning via Attentive CNN

Abstract

Abstract Knowledge graphs have played a significant role in various applications and knowledge reasoning is one of the key tasks. However, the task gets more challenging when each fact is associated with a time annotation on temporal knowledge graph. Most of the existing temporal knowledge graph representation learning methods exploit structural information to learn the entity and relation representations. By these methods, those entities with similar structural information cannot be easily distinguished. Incorporating other information is an effective way to solve such problems. To address this problem, we propose a temporal knowledge graph representation learning method d-HyTE that incorporates entity descriptions. We learn structure-based representations of entities and relations and explore a deep convolutional neural network with attention to encode description-based representations of entities. The joint representation of two different representations of an entity is regarded as the final representation. We evaluate this method on link prediction and temporal scope prediction. Experimental results showed that our method d-HyTE outperformed the other baselines on many metrics.