ChatGPT, Let us Chat Sign Language: Experiments, Architectural Elements, Challenges and Research Directions
This work addresses accessibility for the deaf and hard-of-hearing community by investigating a novel application of ChatGPT, though it is incremental as it adapts an existing model to a new domain.
The paper explored ChatGPT's potential for sign language translation, finding it could accurately translate between English and several sign languages in one prompt iteration but failed in other directions.
ChatGPT is a language model based on Generative AI. Existing research work on ChatGPT focused on its use in various domains. However, its potential for Sign Language Translation (SLT) is yet to be explored. This paper addresses this void. Therefore, we present GPT's evolution aiming a retrospective analysis of the improvements to its architecture for SLT. We explore ChatGPT's capabilities in translating different sign languages in paving the way to better accessibility for deaf and hard-of-hearing community. Our experimental results indicate that ChatGPT can accurately translate from English to American (ASL), Australian (AUSLAN), and British (BSL) sign languages and from Arabic Sign Language (ArSL) to English with only one prompt iteration. However, the model failed to translate from Arabic to ArSL and ASL, AUSLAN, and BSL to Arabic. Consequently, we present challenges and derive insights for future research directions.