TAGCN: Typed Attention Graph Convolutional Networks for Entity Alignment in Cross-lingual Knowledge Graphs
Paper
Paper/Presentation Title | TAGCN: Typed Attention Graph Convolutional Networks for Entity Alignment in Cross-lingual Knowledge Graphs |
---|---|
Presentation Type | Paper |
Authors | Gao, Jianliang, Li, Zhao, Xiong, Fan, Liu, Xiangyue, Xiao, Jie, Wang, Biao and Zhang, Ji |
Journal or Proceedings Title | Proceedings of 2021 IEEE 23rd International Conference on High Performance Computing and Communications (HPCC) |
Journal Citation | pp. 2050-2059 |
Number of Pages | 10 |
Year | 2022 |
Publisher | IEEE (Institute of Electrical and Electronics Engineers) |
Place of Publication | United States |
ISBN | 9781665494571 |
Digital Object Identifier (DOI) | https://doi.org/10.1109/HPCC-DSS-SmartCity-DependSys53884.2021.00306 |
Web Address (URL) of Paper | https://ieeexplore.ieee.org/document/9780986 |
Web Address (URL) of Conference Proceedings | https://ieeexplore.ieee.org/xpl/conhome/9780876/proceeding |
Conference/Event | 2021 IEEE 23rd International Conference on High Performance Computing and Communications (HPCC) |
Event Details | 2021 IEEE 23rd International Conference on High Performance Computing and Communications (HPCC) Delivery In person Event Date 20 to end of 22 Dec 2021 Event Location Hainan, China Rank B B |
Abstract | Cross-lingual entity alignment aims at integrating complementary knowledge graphs (KGs) presented in different languages. It bridges cross-lingual knowledge for knowledge discovery. In this paper, we propose a new embedding-based framework named Typed Attention Graph Convolutional Networks (TAGCN) for cross-lingual entity alignment. In TAGCN, the relation type information is fully utilized with the typed attention mechanism. Then we incorporate entity information and the relation type information of neighbors into entities through attention mechanism to iteratively learn better representation for entities. The experimental results show that our model consistently outperforms the state-of-the-art alignment methods. |
Keywords | graph convolutional network; relation type; entity alignment; knowledge graph |
ANZSRC Field of Research 2020 | 460999. Information systems not elsewhere classified |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | Central South University, China |
Zhejiang University, China | |
Hangzhou Yugu Technology, China | |
Zhejiang Lab, China | |
University of Southern Queensland |
https://research.usq.edu.au/item/z58yq/tagcn-typed-attention-graph-convolutional-networks-for-entity-alignment-in-cross-lingual-knowledge-graphs
61
total views1
total downloads2
views this month0
downloads this month