A Unified Ontology-Based Knowledge Graph Framework for Multi-Domain Vietnamese Legal Document Retrieval
DOI:
https://doi.org/10.56532/mjsat.v6i2.684Keywords:
knowledge graph, legal information retrieval, multi-domain ontology, natural language processing, Vietnamese legal documentsAbstract
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.
References
A. Zalesinska et al., Legal Tech: Information Technology Tools in Justice Administration. Nomos Verlagsgesellschaft, 2021. doi: https://doi.org/10.5771/9783748922834
P. Lewis et al., "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks," Advances in Neural Information Processing Systems, vol. 33, pp. 9459-9474, 2020. doi: https://doi.org/10.48550/arXiv.2005.11401
M. Hofer et al., "Construction of Knowledge Graphs: State and Challenges," Information, vol. 15, no. 8, pp. 1-25, 2024. doi: https://doi.org/10.3390/info15080509
A. Hogan et al., "Knowledge Graphs," ACM Computing Surveys, vol. 54, no. 4, pp. 1-37, 2022. doi: https://doi.org/10.1145/3447772
H. Q. Ngo et al., "Ontology Knowledge Map for Vietnamese Legal Applications," Vietnam Journal of Computer Science, vol. 11, no. 2, pp. 189-210, 2024. doi: https://doi.org/10.1142/S2196888824500015
Bộ Tư pháp Việt Nam, "Thông tư 25/2011/TT-BTP về thể thức và kỹ thuật trình bày văn bản quy phạm pháp luật," Hà Nội, 2011.
D. V. Dang et al., "Knowledge Graph-based Legal Query System with Large Language Models and RAG," Proc. Asian Conference on Intelligent Information and Database Systems, Springer, pp. 156-168, 2025. doi: https://doi.org/10.1007/978-981-97-4985-0_13
Y. Gao et al., "Retrieval-Augmented Generation for Large Language Models: A Survey," arXiv preprint arXiv:2312.10997, 2024. doi: https://doi.org/10.48550/arXiv.2312.10997
Z. Ji et al., "Survey of Hallucination in Natural Language Generation," ACM Computing Surveys, vol. 55, no. 12, pp. 1-38, 2023. doi: https://doi.org/10.1145/3571730
L. Huang et al., "A Survey on Hallucination in Large Language Models," arXiv preprint arXiv:2311.05232, 2023. doi: https://doi.org/10.48550/arXiv.2311.05232
V. T. Pham et al., "Ontology-based Intelligent Searching on Traffic Law Documents," Proc. International Conference on Agents and Artificial Intelligence, pp. 456-463, 2023. doi: https://doi.org/10.5220/0011792600003393
G. Sartor, "Approaches to Legal Ontologies," in Approaches to Legal Ontologies, Springer, pp. 1-14, 2011. doi: https://doi.org/10.1007/978-94-007-0120-5_1
R. Hoekstra et al., "The LKIF Core Ontology of Basic Legal Concepts," Proc. Workshop on Legal Ontologies and Artificial Intelligence Techniques, pp. 43-63, 2007.
D. Dang et al., "Information Retrieval Using Ontology and Graph Embeddings," Proc. Industrial, Engineering and Other Applications of Applied Intelligent Systems, Springer, pp. 287-299, 2023. doi: https://doi.org/10.1007/978-3-031-36822-6_25
A. Gangemi, "Ontology Design Patterns for Semantic Web Content," Proc. International Semantic Web Conference, Springer, pp. 262-276, 2005. doi: https://doi.org/10.1007/11574620_21
D. Q. Nguyen and A. T. Nguyen, "PhoBERT: Pre-trained Language Models for Vietnamese," Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 1037-1042, 2020. doi: https://doi.org/10.18653/v1/2020.findings-emnlp.92
T. S. Nguyen et al., "VnCoreNLP: A Vietnamese Natural Language Processing Toolkit," Proc. NAACL System Demonstrations, pp. 56-60, 2018. doi: https://doi.org/10.18653/v1/N18-5012
Quốc hội Việt Nam, "Luật Đất đai số 31/2024/QH15," Hà Nội, 2024.
Quốc hội Việt Nam, "Luật Giao dịch điện tử số 20/2023/QH15," Hà Nội, 2023.
Quốc hội Việt Nam, "Bộ luật Lao động số 45/2019/QH14," Hà Nội, 2019.
C. Yang et al., "Knowledge Graph and LLM Co-learning via Structure-oriented Retrieval-Augmented Generation," IEEE Data Engineering Bulletin, vol. 48, no. 1, pp. 45-58, 2025.
A. Madaan et al., "Self-Refine: Iterative Refinement with Self-Feedback," Advances in Neural Information Processing Systems, vol. 36, pp. 46534-46594, 2023. doi: https://doi.org/10.48550/arXiv.2303.17651
N. Shinn et al., "Reflexion: Language Agents with Verbal Reinforcement Learning," Advances in Neural Information Processing Systems, vol. 36, pp. 8634-8652, 2023. doi: https://doi.org/10.48550/arXiv.2303.11366
N. Reimers and I. Gurevych, "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks," Proc. EMNLP-IJCNLP, pp. 3982-3992, 2019. doi: https://doi.org/10.18653/v1/D19-1410
S. Robertson and H. Zaragoza, "The Probabilistic Relevance Framework: BM25 and Beyond," Foundations and Trends in Information Retrieval, vol. 3, no. 4, pp. 333-389, 2020. doi: https://doi.org/10.1561/1500000019
V. T. Pham and M. Phan, "Integrating Knowledge Graph with Retrieval-Augmented Generation for Vietnamese Legal Question Answering," DS Journal of Digital Science and Technology, vol. 5, no. 1, pp. 1-13, 2026. doi: https://doi.org/10.59232/DST-V5I1P101
T. V. Pham et al., "A Self-Reflection Mechanism for Reducing Hallucination in Vietnamese Legal Question Answering Systems," Scientific Journal of Computer Science, vol. 2, no. 1, pp. 72-80, 2026. doi: https://doi.org/10.64539/sjcs.v2i1.2026.380
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Vuong Thi Pham, Minh Phan, Cao Bao Quynh, Truong Cong Phuc, Nguyen Thanh Duy, Tien Minh Vy, Nguyen Ngoc Son
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
