Entity Alignment for Cross-Lingual Knowledge Graph with Graph Convolutional Networks

IJCAI 2019 pp. 6480-6481

doi:10.24963/IJCAI.2019/929 /ijcai/2019/xiong2019ijcai-entity/

Abstract

Graph convolutional network (GCN) is a promising approach that has recently been used to resolve knowledge graph alignment. In this paper, we propose a new method to entity alignment for cross-lingual knowledge graph. In the method, we design a scheme of attribute embedding for GCN training. Furthermore, GCN model utilizes the attribute embedding and structure embedding to abstract graph features simultaneously. Our preliminary experiments show that the proposed method outperforms the state-of-the-art GCN-based method.

PDF IJCAI Semantic Scholar

Cite

Text

Xiong and Gao. "Entity Alignment for Cross-Lingual Knowledge Graph with Graph Convolutional Networks." International Joint Conference on Artificial Intelligence, 2019. doi:10.24963/IJCAI.2019/929

Markdown

[Xiong and Gao. "Entity Alignment for Cross-Lingual Knowledge Graph with Graph Convolutional Networks." International Joint Conference on Artificial Intelligence, 2019.](https://mlanthology.org/ijcai/2019/xiong2019ijcai-entity/) doi:10.24963/IJCAI.2019/929

BibTeX

@inproceedings{xiong2019ijcai-entity,
  title     = {{Entity Alignment for Cross-Lingual Knowledge Graph with Graph Convolutional Networks}},
  author    = {Xiong, Fan and Gao, Jianliang},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2019},
  pages     = {6480-6481},
  doi       = {10.24963/IJCAI.2019/929},
  url       = {https://mlanthology.org/ijcai/2019/xiong2019ijcai-entity/}
}