A Statutory Article Retrieval Dataset in French

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics Volume 1: Long Papers, pages 6789 - 6803 May 22-27, 2022 c⃝2022 Association for Computational Linguistics A Statutory Article Retrieval Dataset in French Antoine Louis and Gerasimos Spanakis Law & Tech Lab, Maastricht University {a.louis, jerry.spanakis}@maastrichtuniversity.nl Abstract Statutory article retrieval is the task of automat- ically retrieving law articles relevant to a legal question. While recent advances in natural lan- guage processing have sparked considerable interest in many legal tasks, statutory article retrieval remains primarily untouched due to the scarcity of large-scale and high-quality an- notated datasets. To address this bottleneck, we introduce the Belgian Statutory Article Re- trieval Dataset (BSARD), which consists of 1,100+ French native legal questions labeled by experienced jurists with relevant articles from a corpus of 22,600+ Belgian law articles. Using BSARD, we benchmark several state-of-the- art retrieval approaches, including lexical and dense architectures, both in zero-shot and su- pervised setups. We find that fine-tuned dense retrieval models significantly outperform other systems. Our best performing baseline achieves 74.8% R@100, which is promising for the fea- sibility of the task and indicates there is still room for improvement. By the specificity of the domain and addressed task, BSARD presents a unique challenge problem for future research on legal information retrieval. Our dataset and source code are publicly available. 1 Introduction Legal issues are an integral part of many people’s lives (Ponce et al., 2019). However, the majority of citizens have little to no knowledge about their rights and fundamental legal processes (Balmer et al., 2010). As the Internet has become the pri- mary source of information in response to life prob- lems (Estabrook et al., 2007), people increasingly turn to search engines when faced with a legal is- sue (Denvir, 2016). Nevertheless, the quality of the search engine’s legal help results is currently unsatisfactory, as top results mainly refer people to commercial websites that provide basic informa- tion as a way to advertise for-profit services (Hagan and Li, 2020). On average, only one in five persons obtain help from the Internet to clarify or solve their legal issue (Ponce et al., 2019). As a result, many vulnerable citizens who cannot afford a le- gal expert’s costly assistance are left unprotected or even exploited. This barrier to accessing legal information creates a clear imbalance within the legal system, preventing the right to equal access to justice for all. People do not need legal services in and of themselves; they need the ends that legal services can provide. Recent advances in natural language processing (NLP), combined with the increasing amount of digitized textual data in the legal domain, offer new possibilities to bridge the gap between people and the law. For example, legal judgment prediction (Aletras et al., 2016; Luo et al., 2017; Zhong et al., 2018; Hu et al., 2018; Chen et al., 2019) may assist citizens in finding insightful pat- terns between their case and its outcome. Addition- ally, legal text summarization (Hachey and Grover, …

Content truncated to 500 words