Embedding Method for Knowledge Graph with Densely Defined Ontology
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912307989184512 |
|---|---|
| author | Ugai, Takanori |
| author_facet | Ugai, Takanori |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_02889 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Embedding Method for Knowledge Graph with Densely Defined Ontology Ugai, Takanori Social and Information Networks Artificial Intelligence 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. |
| title | Embedding Method for Knowledge Graph with Densely Defined Ontology |
| topic | Social and Information Networks Artificial Intelligence |
| url | https://arxiv.org/abs/2504.02889 |