MARATTO

dataset · Zenodo (CERN European Organization for Nuclear Research)

MoroccoRegQA

Abstract

MoroccoRegQA is an Arabic regulatory retrieval benchmark comprising 90 expert-annotated query–evidence pairs grounded in five Moroccan legal codes and a parsed corpus of 2,464 hierarchically structured articles (moroccanregdoc.json). Each query is provided in three forms — Moroccan Darija, Modern Standard Arabic (MSA), and English — and is linked to one or more gold evidence articles requiring multi-hop reasoning across the statutory citation graph. The benchmark is designed to evaluate retrieval systems on Arabic morphological ambiguity, hidden definitional cross-references, and hierarchical document structure.

Read the original research

This page summarises published work. The authoritative version sits with the publisher.

DOI: 10.5281/zenodo.21863387

Is something wrong with this record? Report it or request removal.

Discussion

Discuss this research

Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.

No discussion yet. Open the first thread.