Abstract | ||
---|---|---|
Knowledge graph embedding refers to projecting entities and relations in knowledge graph into continuous vector spaces. Current state-of-the-art models are translation-based model, which build embeddings by treating relation as translation from head entity to tail entity. However, previous models is too strict to model the complex and diverse entities and relations(e.g. symmetric/transitive/one-to-many/many-to-many relations). To address these issues, we propose a new principle to allow flexible translation between entity and relation vectors. We can design a novel score function to favor flexible translation for each translation-based models without increasing model complexity. To evaluate the proposed principle, we incorporate it into previous method and conduct triple classification on benchmark datasets. Experimental results show that the principle can remarkably improve the performance compared with several state-of-the-art baselines. |
Year | Venue | Field |
---|---|---|
2016 | KR | Knowledge graph,Monad (category theory),Vector space,Embedding,Computer science,Theoretical computer science,Score,Transitive relation,Model complexity |
DocType | Citations | PageRank |
Conference | 2 | 0.37 |
References | Authors | |
1 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jun Feng | 1 | 29 | 3.20 |
Minlie Huang | 2 | 1260 | 90.68 |
Mingdong Wang | 3 | 2 | 0.37 |
Mantong Zhou | 4 | 5 | 1.09 |
Yu Hao | 5 | 248 | 17.42 |
Xiaoyan Zhu | 6 | 2125 | 141.16 |