Finding the Law: Enhancing Statutory Article Retrieval via Graph Neural Networks

Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2761–2776 May 2-6, 2023 ©2023 Association for Computational Linguistics Finding the Law: Enhancing Statutory Article Retrieval via Graph Neural Networks Antoine Louis Gijs van Dijck Gerasimos Spanakis Law & Tech Lab, Maastricht University {a.louis, gijs.vandijck, jerry.spanakis}@maastrichtuniversity.nl Abstract Statutory article retrieval (SAR), the task of retrieving statute law articles relevant to a le- gal question, is a promising application of le- gal text processing. In particular, high-quality SAR systems can improve the work efficiency of legal professionals and provide basic legal assistance to citizens in need at no cost. Unlike traditional ad-hoc information retrieval, where each document is considered a complete source of information, SAR deals with texts whose full sense depends on complementary infor- mation from the topological organization of statute law. While existing works ignore these domain-specific dependencies, we propose a novel graph-augmented dense statute retriever (G-DSR) model that incorporates the structure of legislation via a graph neural network to improve dense retrieval performance. Experi- mental results show that our approach outper- forms strong retrieval baselines on a real-world expert-annotated SAR dataset.1 1 Introduction Today, the high cost of legal expertise prevents less fortunate people from understanding and reacting to legal issues that may arise (Ponce et al., 2019). In recent years, an increasing number of works have focused on legal text processing (Zhong et al., 2020) with the intent to assist legal practitioners and citizens while reducing legal costs and improv- ing equal access to justice for all. Statutory article retrieval (SAR), the task of retrieving statute law articles relevant to a legal question, marks the first and one of the most crucial steps in any legal aid process. Our goal is to help reduce the gap between people and the law by improving SAR systems that could provide citizens with the first component of a free professional legal aid service. Prior work has addressed SAR with standard in- formation retrieval approaches such as term-based 1Our source code is available at https://github. com/maastrichtlawtech/gdsr. Penal Code Civil Code Rural Code Book 1 Book 2 Book 3 Book M Title 1 Title 2 Title 3 Title 4 Title N Statute Law Section 1 Art. R ... ... ... ... ... ... ... ... ... Chapter 1 Chapter 2 Chapter 3 Chapter 4 Chapter 5 Chapter P ... ... ... ... ... Section Q Section 2 Section 3 Section 4 Section 5 Section 6 ... ... ... ... ... ... Art.101 Art.102 Art.103 Art.104 Art.105 Art.106 Art.107 Art.108 Figure 1: Illustration of the hierarchical organization of statute law. Each law code is structured into books, titles, chapters, and sections. The deeper the divisions, the closer the legal concepts of the articles below them. models or dense embedding-based models (Kim et al., 2019; Nguyen et al., 2021). While good per- formance has been achieved, these approaches rely on the flawed assumption that articles are complete and independent sources of information. In reality, statute law is an …

Content truncated to 500 words