Knowledge Graph Completion via Local Semantic Contexts

摘要: Knowledge graphs are playing an increasingly important role for many search tasks such as entity search, question answering, etc. Although there millions of entities and thousands relations in existing knowledge Freebase DBpedia, they still far from complete. Previous approaches to complete either factor decomposition based methods or machine learning ones. We propose a complementary approach that estimates the likelihood triple on similarity measure some common semantic patterns entities. Such way estimation is very effective which exploits contexts Experimental results demonstrate our model achieves significant improvements graph completion compared with state-of-art techniques.