Embedding Entities and Relations for Learning and Inference in Knowledge Bases

20 Dec 2014Bishan YangWen-tau YihXiaodong HeJianfeng GaoLi Deng

We consider learning representations of entities and relations in KBs using the neural-embedding approach. We show that most existing models, including NTN (Socher et al., 2013) and TransE (Bordes et al., 2013b), can be generalized under a unified learning framework, where entities are low-dimensional vectors learned from a neural network and relations are bilinear and/or linear mapping functions... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Link Prediction WN18 DistMult MRR 0.822 # 14
Link Prediction WN18 DistMult [email protected] 0.936 # 12
Link Prediction WN18 DistMult [email protected] 0.914 # 9
Link Prediction WN18 DistMult [email protected] 0.728 # 11
Link Prediction WN18 DistMult MR 902 # 1