Knowledge Graphs Construction from Criminal Court Appeals: Insights from the French Cassation Court

Abstract

Despite growing interest, accurately and reliably representing unstructured data, such as court decisions, in a structured form, remains a challenge. Recent advancements in generative AI applied to language modeling enabled the transformation of text into knowledge graphs, unlocking new opportunities for analysis and modeling. This paper presents a framework for constructing knowledge graphs from appeals to the French Cassation Court. The framework includes a domain-specific ontology and a derived dataset, offering a foundation for structured legal data representation and analysis.

Alexander Belikov

Researcher, AI Manager

My research interests include graph neural networks, SciSci and Gen AI.