ChatGPT, Let Us Chat Sign Language: Experiments, Architectural Elements, Challenges and Research Directions

Nada Shahin, Leila Ismail

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

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.

Original languageEnglish
Title of host publication2023 International Symposium on Networks, Computers and Communications, ISNCC 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350335590
DOIs
Publication statusPublished - 2023
Event2023 International Symposium on Networks, Computers and Communications, ISNCC 2023 - Doha, Qatar
Duration: Oct 23 2023Oct 26 2023

Publication series

Name2023 International Symposium on Networks, Computers and Communications, ISNCC 2023

Conference

Conference2023 International Symposium on Networks, Computers and Communications, ISNCC 2023
Country/TerritoryQatar
CityDoha
Period10/23/2310/26/23

Keywords

  • AI
  • ChatGPT
  • Decoder
  • Encoder
  • NLP
  • Sign Language Translation
  • Transformer

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Information Systems and Management
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'ChatGPT, Let Us Chat Sign Language: Experiments, Architectural Elements, Challenges and Research Directions'. Together they form a unique fingerprint.

Cite this