中国科学院自动化研究所机构知识库

Knowledge graph embedding aims at learning low-dimensional
representations for entities and relations in knowledge graph. Previous
knowledge graph embedding methods usually assign a score to each triple
in order to measure the plausibility of it. Despite of the effectiveness of
these models, they ignore the fine-grained(matching signals between en-
tities and relations) clues since their scores are mainly obtained by ma-
nipulating the triple as a whole. To address this problem, we instead pro-
pose a model which firstly produce diverse features of entity and relation
by multi-head attention and then introduce the interaction mechanism
to incorporate matching signals between entities and relations. Experi-
ments show that our model achieves better link prediction performance
than multiple strong baselines on two benchmark datasets WN18RR and
FB15k-237.