ChatGPT, Let us Chat Sign Language: Experiments, Architectural Elements, Challenges and Research Directions
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910295979458560 |
|---|---|
| author | Shahin, Nada Ismail, Leila |
| author_facet | Shahin, Nada Ismail, Leila |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_06804 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ChatGPT, Let us Chat Sign Language: Experiments, Architectural Elements, Challenges and Research Directions Shahin, Nada Ismail, Leila Computation and Language Artificial Intelligence I.2.7 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. |
| title | ChatGPT, Let us Chat Sign Language: Experiments, Architectural Elements, Challenges and Research Directions |
| topic | Computation and Language Artificial Intelligence I.2.7 |
| url | https://arxiv.org/abs/2401.06804 |