RDGCN combines dual relation graph attention with highway-gated GCNs to improve cross-lingual entity alignment, reaching 70.75 to 88.64 Hits@1 on DBP15K.
A joint embedding method for entity alignment of knowledge bases
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs
RDGCN combines dual relation graph attention with highway-gated GCNs to improve cross-lingual entity alignment, reaching 70.75 to 88.64 Hits@1 on DBP15K.