For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Leveraging Entity-Type Properties in the Relational Context for Knowledge Graph Embedding
Md Mostafizur RAHMAN Atsuhiro TAKASU
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2020/05/01
Online ISSN: 1745-1361
Type of Manuscript: Special Section PAPER (Special Section on Data Engineering and Information Management)
knowledge representations, entity types, embedding models,
Full Text: PDF(397.7KB)>>
Knowledge graph embedding aims to embed entities and relations of multi-relational data in low dimensional vector spaces. Knowledge graphs are useful for numerous artificial intelligence (AI) applications. However, they (KGs) are far from completeness and hence KG embedding models have quickly gained massive attention. Nevertheless, the state-of-the-art KG embedding models ignore the category specific projection of entities and the impact of entity types in relational aspect. For example, the entity “Washington” could belong to the person or location category depending on its appearance in a specific relation. In a KG, an entity usually holds many type properties. It leads us to a very interesting question: are all the type properties of an entity are meaningful for a specific relation? In this paper, we propose a KG embedding model TPRC that leverages entity-type properties in the relational context. To show the effectiveness of our model, we apply our idea to the TransE, TransR and TransD. Our approach outperforms other state-of-the-art approaches as TransE, TransD, DistMult and ComplEx. Another, important observation is: introducing entity type properties in the relational context can improve the performances of the original translation distance based models.