A practical approach to building legal knowledge graphs from legal texts for legal consultation systems
Tóm tắt: 4
| 
PDF: 5 
##plugins.themes.academic_pro.article.main##
Author
Từ khóa:
Tóm tắt
In the context of applying artificial intelligence to the legal domain, building legal question-answering (QA) systems requires a structured, queryable, and inferable knowledge foundation. This paper proposes a semi-automated method to extract and map legal knowledge from the Penal Code of Vietnam into a knowledge graph, supporting criminal law QA systems. The solution includes five main steps: (1) extracting legal text from the PDF files, (2) preprocessing and normalizing the text into individual articles, (3) using large language models (LLMs) to generate fundamental knowledge components based on the predefined rule set, (4) mapping these components into nodes and edges to construct the knowledge graph, and (5) optimizing and visualizing the graph. Preliminary results show that the model can accurately represent legal relationships such as violations, penalties, applicable subjects, and inter-article references, which will form the groundwork for the future automated legal QA applications.
Tài liệu tham khảo
-
[1] OpenAI, “GPT-4 Technical Report,” arXiv preprint arXiv:2303.08774, 2023.
[2] G. Team et al., “Gemini: A Family of Highly Capable Multimodal Models,” arXiv preprint arXiv:2312.11805, 2023.
[3] S. Zhang, L. Yao, A. Sun, and Y. Tay, “Neural approaches to conversational AI: Question answering, task-oriented dialogues and social chatbots,” Information Fusion, vol. 52, pp. 90–107, 2019.
[4] S. Ji, S. Pan, E. Cambria, P. Marttinen, and P. S. Yu, “A survey on knowledge graphs: Representation, acquisition, and applications,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 2, pp. 494–514, 2021.
[5] T.-H.-Y. Vuong, M.-Q. Hoang, T.-M. Nguyen, H.-T. Nguyen, and H.-T. Nguyen, “Constructing a Knowledge Graph for Vietnamese Legal Cases with Heterogeneous Graphs,” arXiv preprint arXiv:2309.09069, 2023.
[6] B. Dong, H. Yu, and H. Li, “A Knowledge Graph Construction Approach for Legal Domain,” Tehnički vjesnik, vol. 28, no. 2, pp. 357–362, 2021.
[7] Neo4j, “Neo4j Documentation,” neo4j.com. [Online]. Available: https://neo4j.com/docs/ [Accessed September 10, 2025].
[8] I. Robinson, J. Webber, and E. Eifrem, Graph Databases: New Opportunities for Connected Data, 2nd ed. Sebastopol, CA: O’Reilly Media, 2015.
[9] Neo4j, “Neo4j Cypher Manual,” neo4j.com. [Online]. Available: https://neo4j.com/developer/cypher/ [Accessed September 10, 2025].
##plugins.themes.academic_pro.article.sidebar##
