From Rule-Based Models to Deep Learning Transformers Architectures for Natural Language Processing and Sign Language Translation Systems: Survey, Taxonomy and Performance Evaluation

TL;DR

This paper reviews the evolution of sign language translation systems, focusing on deep learning and Transformer architectures, and discusses requirements for real-time, high-quality sign language translation.

Contribution

It provides a comprehensive taxonomy of Transformer-based sign language translation models and outlines future research directions for real-time systems.

Findings

Transformers are the most used approach in sign language translation.

A taxonomy of Transformer architectures for sign language translation is proposed.

Future directions include real-time, high-quality translation systems.

Abstract

With the growing Deaf and Hard of Hearing population worldwide and the persistent shortage of certified sign language interpreters, there is a pressing need for an efficient, signs-driven, integrated end-to-end translation system, from sign to gloss to text and vice-versa. There has been a wealth of research on machine translations and related reviews. However, there are few works on sign language machine translation considering the particularity of the language being continuous and dynamic. This paper aims to address this void, providing a retrospective analysis of the temporal evolution of sign language machine translation algorithms and a taxonomy of the Transformers architectures, the most used approach in language translation. We also present the requirements of a real-time Quality-of-Service sign language ma-chine translation system underpinned by accurate deep learning algorithms. We propose future research directions for sign language translation systems.