English

PPKE: Knowledge Representation Learning by Path-based Pre-training

Computation and Language 2020-12-08 v1 Artificial Intelligence

Abstract

Entities may have complex interactions in a knowledge graph (KG), such as multi-step relationships, which can be viewed as graph contextual information of the entities. Traditional knowledge representation learning (KRL) methods usually treat a single triple as a training unit, and neglect most of the graph contextual information exists in the topological structure of KGs. In this study, we propose a Path-based Pre-training model to learn Knowledge Embeddings, called PPKE, which aims to integrate more graph contextual information between entities into the KRL model. Experiments demonstrate that our model achieves state-of-the-art results on several benchmark datasets for link prediction and relation prediction tasks, indicating that our model provides a feasible way to take advantage of graph contextual information in KGs.

Keywords

Cite

@article{arxiv.2012.03573,
  title  = {PPKE: Knowledge Representation Learning by Path-based Pre-training},
  author = {Bin He and Di Zhou and Jing Xie and Jinghui Xiao and Xin Jiang and Qun Liu},
  journal= {arXiv preprint arXiv:2012.03573},
  year   = {2020}
}