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

Xiai Yan, Yao Yi, Weiqi Shi, Hua Tian and Xin Su
Additional contact information
Xiai Yan: Xiangtan University, China & Hunan Police Academy, China
Yao Yi: Xiangtan University, China
Weiqi Shi: Hunan Police Academy, China
Hua Tian: Hunan Police Academy, China
Xin Su: Hunan Police Academy, China

International Journal on Semantic Web and Information Systems (IJSWIS), 2024, vol. 20, issue 1, 1-18

Abstract: 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.

Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://services.igi-global.com/resolvedoi/resolve ... 0.4018/IJSWIS.336919 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:igg:jswis0:v:20:y:2024:i:1:p:1-18

Access Statistics for this article

International Journal on Semantic Web and Information Systems (IJSWIS) is currently edited by Brij Gupta

More articles in International Journal on Semantic Web and Information Systems (IJSWIS) from IGI Global
Bibliographic data for series maintained by Journal Editor ().