Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs

Association of Computational Linguistics (ACl) 2019 2019 Deepak NathaniJatin ChauhanCharu SharmaManohar Kaul

The recent proliferation of knowledge graphs (KGs) coupled with incomplete or partial information, in the form of missing relations (links) between entities, has fueled a lot of research on knowledge base completion (also known as relation prediction). Several recent works suggest that convolutional neural network (CNN) based models generate richer and more expressive feature embeddings and hence also perform well on relation prediction... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Knowledge Graph Completion FB15k-237 KBAT [email protected] 46 # 1
Knowledge Graph Completion FB15k-237 KBAT [email protected] 54 # 1
Knowledge Graph Completion FB15k-237 KBAT [email protected] 62.6 # 1
Knowledge Graph Completion FB15k-237 KBAT MRR 0.518 # 1
Knowledge Graph Completion FB15k-237 KBAT MR 210 # 1
Knowledge Graph Completion WN18RR KBAT [email protected] 36.1 # 1
Knowledge Graph Completion WN18RR KBAT [email protected] 48.3 # 1
Knowledge Graph Completion WN18RR KBAT [email protected] 58.1 # 1