Publication
Continual Learning in Multilingual Sign Language Translation
Shakib Yazdani; Josef van Genabith; Cristina España-Bonet
In: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL-2025), April 29 - May 4, Albuquerque, New Mexico, USA, Pages 10923-10938, Association for Computational Linguistics, 2025.
Abstract
The field of sign language translation (SLT) is still in its infancy, as evidenced by the low translation quality, even when using deep learn- ing approaches. Probably because of this, many common approaches in other machine learning fields have not been explored in sign language. Here, we focus on continual learning for mul- tilingual SLT. We experiment with three con- tinual learning methods and compare them to four more naive baseline and fine-tuning ap- proaches. We work with four sign languages (ASL, BSL, CSL and DGS) and three spo- ken languages (Chinese, English and German). Our results show that incremental fine-tuning is the best performing approach both in terms of translation quality and transfer capabilities, and that continual learning approaches are not yet fully competitive given the current SOTA in SLT.