@inproceedings{ashraf-etal-2026-urdu,
title = "{U}rdu-{CLEVR}: A Novel Benchmark for Visual Reasoning in an Under-Resourced Linguistic Context",
author = "Ashraf, Sohail and
Zafar, Adeel and
Nowaczyk, Slawomir and
Sajid, Ahthasham",
editor = "Ojha, Atul Kr. and
Sakti, Sakriani and
Soria, Claudia and
Melero, Maite and
McCrae, John P. and
Lignos, Constantine and
Liu, Chao-Hong and
Claramunt, German Rigau and
Rehm, Georg",
booktitle = "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",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.sigul-1.8/",
doi = "10.63317/4ow3ni9a2kiw",
pages = "74--82",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ashraf-etal-2026-urdu">
<titleInfo>
<title>Urdu-CLEVR: A Novel Benchmark for Visual Reasoning in an Under-Resourced Linguistic Context</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sohail</namePart>
<namePart type="family">Ashraf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adeel</namePart>
<namePart type="family">Zafar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Slawomir</namePart>
<namePart type="family">Nowaczyk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahthasham</namePart>
<namePart type="family">Sajid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>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</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="given">Rigau</namePart>
<namePart type="family">Claramunt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">ashraf-etal-2026-urdu</identifier>
<identifier type="doi">10.63317/4ow3ni9a2kiw</identifier>
<location>
<url>https://aclanthology.org/2026.sigul-1.8/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>74</start>
<end>82</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Urdu-CLEVR: A Novel Benchmark for Visual Reasoning in an Under-Resourced Linguistic Context
%A Ashraf, Sohail
%A Zafar, Adeel
%A Nowaczyk, Slawomir
%A Sajid, Ahthasham
%Y Ojha, Atul Kr.
%Y Sakti, Sakriani
%Y Soria, Claudia
%Y Melero, Maite
%Y McCrae, John P.
%Y Lignos, Constantine
%Y Liu, Chao-Hong
%Y Claramunt, German Rigau
%Y Rehm, Georg
%S 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
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca, Spain
%F ashraf-etal-2026-urdu
%X 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.
%R 10.63317/4ow3ni9a2kiw
%U https://aclanthology.org/2026.sigul-1.8/
%U https://doi.org/10.63317/4ow3ni9a2kiw
%P 74-82
Markdown (Informal)
[Urdu-CLEVR: A Novel Benchmark for Visual Reasoning in an Under-Resourced Linguistic Context](https://aclanthology.org/2026.sigul-1.8/) (Ashraf et al., SIGUL-EURALI-DCLRL 2026)
ACL