Embedding Method for Knowledge Graph with Densely Defined Ontology
By: Takanori Ugai
Potential Business Impact:
Helps computers understand information better.
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.
Similar Papers
On Large-scale Evaluation of Embedding Models for Knowledge Graph Completion
Machine Learning (CS)
Fixes how computers learn facts from data.
Injecting Knowledge Graphs into Large Language Models
Machine Learning (CS)
Helps computers understand facts better.
STCKGE:Continual Knowledge Graph Embedding Based on Spatial Transformation
Information Retrieval
Teaches computers to remember new facts better.