Improvement of Web Semantic and Transformer-Based Knowledge Graph Completion in Low-Dimensional Spaces

In recent years, knowledge graph completion (KGC) has garnered significant attention. However, noise in the graph poses numerous challenges to the completion of tasks, including error propagation, missing information, and misleading relations. Many existing KGC methods utilize the multi-head self-at...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal on semantic web and information systems 2024-01, Vol.20 (1), p.1-18
Hauptverfasser: Yan, Xiai, Yi, Yao, Shi, Weiqi, Tian, Hua, Su, Xin
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In recent years, knowledge graph completion (KGC) has garnered significant attention. However, noise in the graph poses numerous challenges to the completion of tasks, including error propagation, missing information, and misleading relations. Many existing KGC methods utilize the multi-head self-attention mechanism (MHA) in transformers, which yields favorable results in low-dimensional space. Nevertheless, employing MHA introduces the risk of overfitting due to a large number of additional parameters, and the choice of model loss function is not comprehensive enough to capture the semantic discriminatory nature between entities and relationships and the treatment of RDF indicates that the dataset contains only positive (training) examples, and the error facts are not encoded, which tends to cause overgeneralization.
ISSN:1552-6283
1552-6291
DOI:10.4018/IJSWIS.336919