aiqbench analysis
The article introduces SyriSign, a new dataset and benchmark for text-to-Syrian Arabic Sign Language translation, addressing the critical lack of resources in low-resource sign languages. The study evaluates generative deep learning architectures like MotionCLIP and T2M-GPT to demonstrate their potential while highlighting current limitations due to small sample sizes. This work is significant for advancing inclusive AI applications that bridge communication gaps for Deaf communities using specific linguistic contexts.
SyriSign: A Parallel Corpus for Arabic Text to Syrian Arabic Sign Language Translation
arXiv:2603.29219v2 Announce Type: replace-cross Abstract: Sign language is the primary approach of communication for the Deaf and Hard-of-Hearing (DHH) community. While there are numerous benchmarks for high-resource sign languages, low-resource languages like Arabic remain underrepresented. Currently, there is no publicly available dataset for Syrian Arabic Sign Language (SyArSL). To overcome this gap, we introduce SyriSign, a dataset comprising 1500 video samples across 150 unique lexical signs, designed for text-to-SyArSL translation tasks. This work aims to reduce communication barriers in Syria, as most news are delivered in spoken or written Arabic, which is often inaccessible to the deaf community. We evaluated SyriSign using three deep learning architectures: MotionCLIP for semantic motion generation, T2M-GPT for text-conditioned motion synthesis, and SignCLIP for bilingual embedding alignment. Experimental results indicate that while generative approaches show strong potential for sign representation, the limited dataset size constrains generalization performance. We will release SyriSign publicly, hoping it serves as an initial benchmark.
Abstract:Sign language is the primary approach of communication for the Deaf and Hard-of-Hearing (DHH) community. While there are numerous benchmarks for high-resource sign languages, low-resource languages like Arabic remain underrepresented. Currently, there is no publicly available dataset for Syrian Arabic Sign Language (SyArSL). To overcome this gap, we introduce SyriSign, a dataset comprising 1500 video samples across 150 unique lexical signs, designed for text-to-SyArSL translation tasks. This work aims to reduce communication barriers in Syria, as most news are delivered in spoken or written Arabic, which is often inaccessible to the deaf community. We evaluated SyriSign using three deep learning architectures: MotionCLIP for semantic motion generation, T2M-GPT for text-conditioned motion synthesis, and SignCLIP for bilingual embedding alignment. Experimental results indicate that while generative approaches show strong potential for sign representation, the limited dataset size constrains generalization performance. We will release SyriSign publicly, hoping it serves as an initial benchmark.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Human-Computer Interaction (cs.HC)
arXiv:2603.29219 [cs.CL]
(or arXiv:2603.29219v2 [cs.CL] for this version)
Full text under the publisher's open licence · 173 words
Related coverage
Corpus Augmentation for Sign Language Translation via LLM-Guided Video Stitching
arXiv · Jun 12, 2026
Bridging Scientific Heritage: An Arabic--Russian Parallel Corpus and LLM Benchmark for Sustainable Knowledge Transfer
arXiv · Sep 15, 2026
MudawanSn: A Gold-Standard Wolof-Arabic Parallel Corpus for Machine Translation
arXiv · Sep 17, 2026
Direct Translation between Sign Languages
arXiv · Oct 1, 2026