Embedding Method for Knowledge Graph with Densely Defined Ontology
This work addresses a specific limitation in knowledge graph completion for domains with densely defined ontologies, but it is incremental as it builds on existing embedding methods.
The paper tackles the underutilization of ontologies in knowledge graph embedding by proposing TransU, a model that treats properties as entities for unified representation, achieving competitive results on standard and practical datasets.
Knowledge graph embedding (KGE) is a technique that enhances knowledge graphs by addressing incompleteness and improving knowledge retrieval. A limitation of the existing KGE models is their underutilization of ontologies, specifically the relationships between properties. This study proposes a KGE model, TransU, designed for knowledge graphs with well-defined ontologies that incorporate relationships between properties. The model treats properties as a subset of entities, enabling a unified representation. We present experimental results using a standard dataset and a practical dataset.