Urdu-CLEVR: A Novel Benchmark for Visual Reasoning in an Under-Resourced Linguistic Context

Sohail Ashraf, Adeel Zafar, Slawomir Nowaczyk, Ahthasham Sajid


Abstract
Visual Question Answering (VQA) bridges the gap between computer vision and natural language processing, yet progress remains largely confined to high-resource languages. For low-resource languages like Urdu, research is severely hindered by the total absence of large-scale reasoning-based datasets. To address this critical gap, we introduce the first synthetic Urdu VQA dataset modeled after the CLEVR framework, specifically designed to evaluate complex, multi-step visual reasoning. We conduct a rigorous comparative analysis using both transformer-based architectures (VisualBERT, LXMERT, ViLT) and neuro-symbolic models. Our results demonstrate that the neuro-symbolic approach achieves a superior accuracy of 85.3%, outperforming the strongest transformer baseline by 7.1% while maintaining competitive processing efficiency. This work establishes a primary benchmark for Urdu VQA, demonstrating that hybrid reasoning architectures provide a robust and scalable solution for advancing multimodal AI in under-resourced linguistic contexts.
Anthology ID:
2026.sigul-1.8
Volume:
Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages
Month:
May
Year:
2026
Address:
Palma, Mallorca, Spain
Editors:
Atul Kr. Ojha, Sakriani Sakti, Claudia Soria, Maite Melero, John P. McCrae, Constantine Lignos, Chao-Hong Liu, German Rigau Claramunt, Georg Rehm
Venues:
SIGUL | EURALI | DCLRL | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
74–82
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-sigul-08
DOI:
10.63317/4ow3ni9a2kiw
Bibkey:
Cite (ACL):
Sohail Ashraf, Adeel Zafar, Slawomir Nowaczyk, and Ahthasham Sajid. 2026. Urdu-CLEVR: A Novel Benchmark for Visual Reasoning in an Under-Resourced Linguistic Context. In Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages, pages 74–82, Palma, Mallorca, Spain. ELRA Language Resources Association (ELRA).
Cite (Informal):
Urdu-CLEVR: A Novel Benchmark for Visual Reasoning in an Under-Resourced Linguistic Context (Ashraf et al., SIGUL-EURALI-DCLRL 2026)
Copy Citation: