Saudi Sign Language Translation Using T5
This work addresses sign language translation for Saudi users, with incremental improvements through cross-linguistic transfer from ASL data.
This paper tackles Saudi Sign Language (SSL) translation by applying T5 models to a novel SSL dataset with challenging testing protocols and unique characteristics like face coverings. The result shows that pre-training on American Sign Language (ASL) data improves performance by roughly 3× in BLEU-4, demonstrating cross-linguistic transferability.
This paper explores the application of T5 models for Saudi Sign Language (SSL) translation using a novel dataset. The SSL dataset includes three challenging testing protocols, enabling comprehensive evaluation across different scenarios. Additionally, it captures unique SSL characteristics, such as face coverings, which pose challenges for sign recognition and translation. In our experiments, we investigate the impact of pre-training on American Sign Language (ASL) data by comparing T5 models pre-trained on the YouTubeASL dataset with models trained directly on the SSL dataset. Experimental results demonstrate that pre-training on YouTubeASL significantly improves models' performance (roughly $3\times$ in BLEU-4), indicating cross-linguistic transferability in sign language models. Our findings highlight the benefits of leveraging large-scale ASL data to improve SSL translation and provide insights into the development of more effective sign language translation systems. Our code is publicly available at our GitHub repository.