HATL: Hierarchical Adaptive-Transfer Learning Framework for Sign Language Machine Translation

Computer Science > Computation and Language [Submitted on 26 Feb 2026] HATL: Hierarchical Adaptive-Transfer Learning Framework for Sign Language Machine Translation Nada Shahin, Leila Ismail Sign Language Machine Translation (SLMT) aims to bridge communication between Deaf and hearing individuals. However, its progress is constrained by scarce datasets, limited signer diversity, and large domain gaps between sign motion patterns and pretrained representations. Existing transfer learning approaches in SLMT are static and often lead to overfitting. These challenges call for the development of an adaptive framework that preserves pretrained structure while remaining robust across linguistic and signing variations. To fill this void, we propose a Hierarchical Adaptive Transfer Learning (HATL) framework, where pretrained layers are progressively and dynamically unfrozen based on training performance behavior. HATL combines dynamic unfreezing, layer-wise learning rate decay, and stability mechanisms to preserve generic representations while adapting to sign characteristics. We evaluate HATL on Sign2Text and Sign2Gloss2Text translation tasks using a pretrained ST-GCN++ backbone for feature extraction and the Transformer and an adaptive transformer (ADAT)for translation. To ensure robust multilingual generalization, we evaluate the proposed approach across three datasets: RWTH-PHOENIXWeather-2014 (PHOENIX14T), Isharah, and MedASL. Experimental results show that HATL consistently outperforms traditional transfer learning approaches across tasks and models, with ADAT achieving BLEU-4 improvements of 15.0% on PHOENIX14T and Isharah and 37.6% on MedASL. Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Computers and Society (cs.CY); Emerging Technologies (cs.ET) ACM classes: I.2.6; I.2.7; I.2.10; I.4.8; I.4.9; I.4.10 Cite as: arXiv:2603.19260 [cs.CL]   (or arXiv:2603.19260v1 [cs.CL] for this version)   https://doi.org/10.48550/arXiv.2603.19260 Focus to learn more Submission history From: Leila Ismail Prof. [view email] [v1] Thu, 26 Feb 2026 17:22:42 UTC (1,177 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CL < prev   |   next > new | recent | 2026-03 Change to browse by: cs cs.AI cs.CV cs.CY cs.ET References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)