A Unified Ontology-Based Knowledge Graph Framework for Multi-Domain Vietnamese Legal Document Retrieval
Malaysian Journal of Science and Advanced Technology · 25.06.2026 · 241-248
DOI: 10.56532/mjsat.v6i2.684 ↗Kurz gefasst
Fachartikel in der Zeitschrift Malaysian Journal of Science and Advanced Technology, online erschienen am 25.06.2026. Verfasst von Vuong Thi Pham und 6 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Legal information retrieval systems face the challenge of handling diverse legal domains with varying terminology, document structures, and semantic relationships. This paper presents a unified ontology-based knowledge graph framework that enables consistent knowledge representation and retrieval across multiple Vietnamese legal domains. The objective of this study is to develop a modular architecture that maximizes reuse while accommodating domain-specific requirements. Our methodology extends the Legal-Onto model with a three-layer architecture: Core Layer defining fundamental legal document structures based on Vietnamese legal formatting regulations, Domain Extension Layer providing specialized concept hierarchies for different legal areas, and Application Layer implementing query interfaces with natural language processing pipelines. The framework is validated through implementation and evaluation across three distinct legal domains: Land Law, Electronic Transaction Law, and Labor Law, comprising 53 legal documents with 1,398 concepts and 5,257 relationships. The results demonstrate that the unified framework achieves average accuracy of 84.2% and F1-score of 0.843 across all domains. Cross-domain evaluation reveals that domain-specific ontology extensions improve retrieval precision by 12.7% compared to generic approaches, while the shared core structure enables knowledge transfer and reduces development effort by 40% per new domain. In conclusion, the modular ontology architecture effectively balances reusability with domain specificity, providing a practical foundation for scalable legal information systems.
Zitieren
APA
Pham, V. T., Phan, M., Quynh, C. B., Phuc, T. C., Duy, N. T., Vy, T. M., & Son, N. N. (2026). A Unified Ontology-Based Knowledge Graph Framework for Multi-Domain Vietnamese Legal Document Retrieval. Malaysian Journal of Science and Advanced Technology, 241-248. https://doi.org/10.56532/mjsat.v6i2.684
Vancouver
Pham VT, Phan M, Quynh CB, Phuc TC, Duy NT, Vy TM, et al. A Unified Ontology-Based Knowledge Graph Framework for Multi-Domain Vietnamese Legal Document Retrieval. Malaysian Journal of Science and Advanced Technology. 2026:241-248. doi:10.56532/mjsat.v6i2.684
BibTeX
@article{Pham2026,
author = {Pham, Vuong Thi and Phan, Minh and Quynh, Cao Bao and Phuc, Truong Cong and Duy, Nguyen Thanh and Vy, Tien Minh and Son, Nguyen Ngoc},
title = {A Unified Ontology-Based Knowledge Graph Framework for Multi-Domain Vietnamese Legal Document Retrieval},
journal = {Malaysian Journal of Science and Advanced Technology},
year = {2026},
pages = {241--248},
doi = {10.56532/mjsat.v6i2.684}
}
EUVIMED