Representation Learning with Ordered Relation Paths for Knowledge Graph Completion

IJCNLP 2019 Yao ZhuHongzhi LiuZhonghai WuYang SongTao Zhang

Incompleteness is a common problem for existing knowledge graphs (KGs), and the completion of KG which aims to predict links between entities is challenging. Most existing KG completion methods only consider the direct relation between nodes and ignore the relation paths which contain useful information for link prediction... (read more)

PDF Abstract IJCNLP 2019 PDF IJCNLP 2019 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Link Prediction FB15k OPTransE MR 33 # 3
[email protected] 0.899 # 5
Link Prediction WN18 OPTransE [email protected] 0.957 # 6
MR 199 # 4

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet