Hybrid AI Enhancing European Drafting Legislation for a Better Regulation
Michele Corazza, Generoso Longo, Leonardo Zilli, Emanuele Di Sante, Salvatore Sapienza, Monica Palmirani · 2025
This study investigates whether AI and ML tools can support European legislative drafting with advanced information retrieval using AI and which methods are more effective. The article proposes hybrid methods leveraging the combination of XML-annotated (Akoma Ntoso) texts and Natural Language Processing techniques that take advantage of the structure of the legal text to perform their tasks. In particular, the experiments conducted in this paper deal with three crucial functionalities for retrieving relevant legislative information with incomplete inputs using thematic similarity: normative references, legislative definitions, and legislative argument search. The study shows that computational approaches combining XML-based documents and Natural Language Processing (NLP) techniques can fruitfully support legal drafting tasks in European legislative institutions.