GNN-ERE: A Graph Neural Network Framework for Entity-Relation Extraction and Intelligent Legal Case Reasoning

Hongdian Ma

Abstract


The construction of legal knowledge graphs and intelligent case reasoning systems is pivotal for enhancing legal information retrieval, case analysis, and judicial decision-making. This research focuses on utilizing graph neural networks (GNNs) to model complex legal entities and their interrelations for structured legal knowledge representation. Traditional methods often rely on keyword matching and shallow semantic analysis, which struggle to capture deep legal logic, implicit correlations, and multi-level entity relations, leading to low reasoning accuracy and limited adaptability. To address these challenges, this paper proposes a novel Graph Neural Network with Entity-Relation Extraction (GNN-ERE) framework. It automatically constructs a legal knowledge graph by extracting entities and relationships from legal texts and integrates it with graph-based reasoning to support intelligent case analysis and precedent retrieval. The proposed method enables automated legal case reasoning by identifying similar legal cases based on contextual and structural similarities within the knowledge graph, thereby supporting judges and legal practitioners in evidence-based decision-making. Experimental results demonstrate that the GNN-ERE framework significantly improves the accuracy of legal case similarity matching and reasoning, enhances the interpretability of the system, and provides a scalable solution for legal AI applications. The proposed method gradually improves the entity extraction accuracy by 89.3%, relation extraction precision by 96%, graph construction time by 9.8 ms, case similarity score by 95%, classification accuracy by 94%, and reasoning time efficiency by 298 ms.


Full Text:

PDF

References


Abu-Salih, B., Al-Tawil, M., Aljarah, I., Faris, H., Wongthongtham, P., Chan, K. Y., & Beheshti, A. (2021). Relational learning analysis of social politics using knowledge graph embedding. Data Mining and Knowledge Discovery, 35(4), 1497-1536.https://doi.org/10.1007/s10618-021-00760-w

Li, H., Wang, Y., Zhang, S., Song, Y., & Qu, H. (2021). KG4Vis: A knowledge graph-based approach for visualization recommendation. IEEE Transactions on Visualization and Computer Graphics, 28(1), 195-205.DOI: 10.1109/TVCG.2021.3114863

Ye, Z., Kumar, Y. J., Sing, G. O., Song, F., & Wang, J. (2022). A comprehensive survey of graph neural networks for knowledge graphs. IEEE Access, 10, 75729-75741.DOI: 10.1109/ACCESS.2022.3191784

Liu, Y., Ding, J., Fu, Y., & Li, Y. (2023). Urbankg: An urban knowledge graph system. ACM Transactions on Intelligent Systems and Technology, 14(4), 1-25.https://doi.org/10.1145/3588577

Wang, Y., Lipka, N., Rossi, R. A., Siu, A., Zhang, R., & Derr, T. (2024, March). Knowledge graph prompting for multi-document question answering. In Proceedings of the AAAI conference on artificial intelligence (Vol. 38, No. 17, pp. 19206-19214).https://doi.org/10.48550/arXiv.2308.11730

Ren, Y., Xiao, Y., Zhou, Y., Zhang, Z., & Tian, Z. (2022). CSKG4APT: A cybersecurity knowledge graph for advanced persistent threat organization attribution. IEEE Transactions on Knowledge and Data Engineering, 35(6), 5695-5709.DOI: 10.1109/TKDE.2022.3175719

Chandak, P., Huang, K., & Zitnik, M. (2023). Building a knowledge graph to enable precision medicine. Scientific Data, 10(1), 67.https://doi.org/10.1038/s41597-023-01960-3

Husainat, M. (2024). Exploiting graphics processing units to speed up subgraph enumeration for efficient graph pattern mining GraphDuMato. PatternIQ Mining, 1(2), 1–12. https://doi.org/10.70023/piqm24121

Li, D., Li, Z., Yang, Y., Sun, L., An, D., & Yang, Q. (2024). Knowledge graph-enhanced large language model for domain-specific question answering systems. Authorea Preprints.

DOI: 10.36227/techrxiv.172963127.77889256/v1

Galkin, M., Yuan, X., Mostafa, H., Tang, J., & Zhu, Z. (2023). Towards foundation models for knowledge graph reasoning. arXiv preprint arXiv:2310.04562.

https://doi.org/10.48550/arXiv.2310.04562

Zhou, J., Chen, X., Zhang, H., & Li, Z. (2024). Automatic knowledge graph construction for judicial cases. arXiv preprint arXiv:2404.09416.

https://doi.org/10.48550/arXiv.2404.09416

Yu, H., & Li, H. (2021). A knowledge graph construction approach for legal domain. Tehnički vjesnik, 28(2), 357-362. https://doi.org/10.17559/TV-20201119084338

Chen, Y., Chen, M., Zhu, Y., Pei, J., Chen, S., Zhou, Y., ... & Zhang, S. (2024). Leverage knowledge graph and large language model for law article recommendation: A case study of chinese criminal law. arXiv preprint arXiv:2410.04949. https://doi.org/10.48550/arXiv.2410.04949

Wu, X., Duan, J., Pan, Y., & Li, M. (2023). Medical knowledge graph: Data sources, construction, reasoning, and applications. Big data mining and analytics, 6(2), 201-217. DOI: 10.26599/BDMA.2022.9020021

Cui, J., Ning, M., Li, Z., Chen, B., Yan, Y., Li, H., ... & Yuan, L. (2023). Chatlaw: A multi-agent collaborative legal assistant with knowledge graph enhanced mixture-of-experts large language model. arXiv preprint arXiv:2306.16092. https://doi.org/10.48550/arXiv.2306.16092

Zhu, Y., Wang, X., Chen, J., Qiao, S., Ou, Y., Yao, Y., ... & Zhang, N. (2024). Llms for knowledge graph construction and reasoning: Recent capabilities and future opportunities. World Wide Web, 27(5), 58. https://doi.org/10.48550/arXiv.2305.13168

Gan, L., Ye, B., Huang, Z., Xu, Y., Chen, Q., & Shu, Y. (2023). Knowledge graph construction based on ship collision accident reports to improve maritime traffic safety. Ocean & Coastal Management, 240, 106660.https://doi.org/10.1016/j.ocecoaman.2023.106660

Liu, H., Zhou, S., Chen, C., Gao, T., Xu, J., & Shu, M. (2022). Dynamic knowledge graph reasoning based on deep reinforcement learning. Knowledge-based systems, 241, 108235. https://doi.org/10.1016/j.knosys.2022.108235

Kosasih, E. E., Margaroli, F., Gelli, S., Aziz, A., Wildgoose, N., & Brintrup, A. (2024). Towards knowledge graph reasoning for supply chain risk management using graph neural networks. International Journal of Production Research, 62(15), 5596-5612. https://doi.org/10.1080/00207543.2022.2100841

Zhou, C., Wang, H., Wang, C., Hou, Z., Zheng, Z., Shen, S., ... & Zhu, Y. (2021). Geoscience knowledge graph in the big data era. Science China Earth Sciences, 64(7), 1105-1114. https://doi.org/10.1007/s11430-020-9750-4

Wang, J., Wang, X., Ma, C., & Kou, L. (2021). A survey on the development status and application prospects of knowledge graph in smart grids. IET Generation, Transmission & Distribution, 15(3), 383-407.

https://doi.org/10.48550/arXiv.2211.00901

Yang, X., Peng, G., Zhang, D., & Lv, Y. (2022). An enhanced intrusion detection system for IoT networks based on deep learning and knowledge graph. Security and Communication Networks, 2022(1), 4748528. https://doi.org/10.1155/2022/4748528

Rajabi, E., & Etminani, K. (2024). Knowledge-graph-based explainable AI: A systematic review. Journal of information science, 50(4), 1019-1029. DOI: 10.1177/01655515221112844

Tamašauskaitė, G., & Groth, P. (2023). Defining a knowledge graph development process through a systematic review. ACM Transactions on Software Engineering and Methodology, 32(1), 1-40. https://doi.org/10.1145/3522586

https://www.kaggle.com/datasets/amohankumar/legal-text-classification-dataset?utm_source




DOI: https://doi.org/10.31449/inf.v49i25.10883

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.