Please use this identifier to cite or link to this item:
Title: Semi-supervised Entity Alignment via Joint Knowledge Embedding Model and Cross-graph Model
Authors: Chengjiang Li
Yixin Cao 
Lei Hou
Jiaxin Shi
Juanzi Li
Tat-Seng Chua 
Issue Date: 3-Nov-2019
Citation: Chengjiang Li, Yixin Cao, Lei Hou, Jiaxin Shi, Juanzi Li, Tat-Seng Chua (2019-11-03). Semi-supervised Entity Alignment via Joint Knowledge Embedding Model and Cross-graph Model. EMNLP 2019 : 2723-2732. ScholarBank@NUS Repository.
Abstract: Entity alignment aims at integrating complementary knowledge graphs (KGs) from different sources or languages, which may benefit many knowledge-driven applications. It is challenging due to the heterogeneity of KGs and limited seed alignments. In this paper, we propose a semi-supervised entity alignment method by joint Knowledge Embedding model and Cross-Graph model (KECG). It can make better use of seed alignments to propagate over the entire graphs with KG-based constraints. Specifically, as for the knowledge embedding model, we utilize TransE to implicitly complete two KGs towards consistency and learn relational constraints between entities. As for the cross-graph model, we extend Graph Attention Network (GAT) with projection constraint to robustly encode graphs, and two KGs share the same GAT to transfer structural knowledge as well as to ignore unimportant neighbors for alignment via attention mechanism. Results on publicly available datasets as well as further analysis demonstrate the effectiveness of KECG. Our codes can be found in https: //
Source Title: EMNLP 2019
DOI: 10.18653/v1/D19-1274
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
D19-1274.pdf1.6 MBAdobe PDF



Page view(s)

checked on Dec 4, 2020

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.