Augmenting Embedding Projection With Entity Descriptions for Knowledge Graph Completion

Extra information, such as hierarchical entity types, entity descriptions or some text corpus are recently used to enhance Knowledge Graph Completion (KGC). A typical task in this setting is building entities’ description information into some embedding models. Existing approaches under this task usually use simple embedding models, which have difficulty in handling the complex structures of the knowledge graphs. These models are also limited in the way where description representation is combined with structure representation, which requires an impractical large set of weight parameters increasing in proportion to the number of entities in the knowledge graph. This paper aims at developing more effective embedding models that jointly represent the structure information of the knowledge base with the description of entities and efficiently reduce the model parameters. We propose more principled approaches named Dimensional Attentive Combination (DAC) for the composition of structure representation and description representation with fixed-size parameters independent of entity amount, and the composition builds upon more powerful knowledge graph embedding models. The proposed model significantly reduces the weight parameters and can extend to KGs with a large set of entities or involving sparse data. Experimental comparison on link prediction and relation prediction shows that our approaches, even under a simple description-encoding model, improve upon the baselines by a significant margin.

Abstract licence: CC BY-NC-ND

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.