GLoT: A Novel Gated-Logarithmic Transformer for Efficient Sign Language Translation
It addresses communication challenges for the Deaf and Hard of Hearing community, but appears incremental as it builds on existing Transformer-based methods for SLMT.
The paper tackles the problem of low performance in Sign Language Machine Translation (SLMT) due to the dynamic nature of sign language, proposing a Gated-Logarithmic Transformer (GLoT) that captures long-term temporal dependencies and consistently outperforms baseline models across all metrics.
Machine Translation has played a critical role in reducing language barriers, but its adaptation for Sign Language Machine Translation (SLMT) has been less explored. Existing works on SLMT mostly use the Transformer neural network which exhibits low performance due to the dynamic nature of the sign language. In this paper, we propose a novel Gated-Logarithmic Transformer (GLoT) that captures the long-term temporal dependencies of the sign language as a time-series data. We perform a comprehensive evaluation of GloT with the transformer and transformer-fusion models as a baseline, for Sign-to-Gloss-to-Text translation. Our results demonstrate that GLoT consistently outperforms the other models across all metrics. These findings underscore its potential to address the communication challenges faced by the Deaf and Hard of Hearing community.