{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-statutory-article-retrieval-dataset-in","title":"A Statutory Article Retrieval Dataset in French","arxiv_id":"2108.11792","date":"2021-08-26","proceeding":"ACL 2022 5","authors":["Antoine Louis","Gerasimos Spanakis"],"abstract":"Statutory article retrieval is the task of automatically retrieving law articles relevant to a legal question. While recent advances in natural language 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 annotated datasets. To address this bottleneck, we introduce the Belgian Statutory Article Retrieval 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 supervised 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 feasibility 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.","url_abs":"https://arxiv.org/abs/2108.11792v2","url_pdf":"https://arxiv.org/pdf/2108.11792v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-statutory-article-retrieval-dataset-in","repo_url":"https://github.com/maastrichtlawtech/bsard","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"specificity","task_name":"Specificity"}],"methods":[{"method_slug":"cbow-word2vec","method_name":"CBoW Word2Vec"},{"method_slug":"roberta","method_name":"RoBERTa"},{"method_slug":"fasttext","method_name":"fastText"}],"datasets_introduced":[{"slug":"bsard","name":"BSARD","full_name":"Belgian Statutory Article Retrieval Dataset"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/information-retrieval-on-bsard","task":"Information Retrieval","dataset":"BSARD","model":"Two-tower Bi-Encoder (RoBERTa)","rank_in_archive_order":1,"of":3,"metrics":{"Recall@100":"74.78","Recall@200":"78.04","Recall@500":"83.39"},"uses_additional_data":false},{"leaderboard":"/sota/information-retrieval-on-bsard","task":"Information Retrieval","dataset":"BSARD","model":"Siamese Bi-Encoder (RoBERTa)","rank_in_archive_order":2,"of":3,"metrics":{"Recall@100":"71.63","Recall@200":"78.38","Recall@500":"83.77"},"uses_additional_data":false},{"leaderboard":"/sota/information-retrieval-on-bsard","task":"Information Retrieval","dataset":"BSARD","model":"BM25","rank_in_archive_order":3,"of":3,"metrics":{"Recall@100":"51.33","Recall@200":"56.78","Recall@500":"64.71"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.11792","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}