Sign Language Sense Disambiguation

TL;DR

This paper investigates how transformer models focusing on different body parts, like hands or mouth, can improve sign language disambiguation, enhancing translation accuracy for German sign language especially in varying dataset sizes.

Contribution

It introduces a body-part focused transformer approach for sign language disambiguation, demonstrating how different body parts influence performance in small versus large datasets.

Findings

Mouth-focused models perform better with small datasets.

Hand-focused models excel with larger datasets.

Results improve sign language translation accuracy.

Abstract

This project explores methods to enhance sign language translation of German sign language, specifically focusing on disambiguation of homonyms. Sign language is ambiguous and understudied which is the basis for our experiments. We approach the improvement by training transformer-based models on various bodypart representations to shift the focus on said bodypart. To determine the impact of, e.g., the hand or mouth representations, we experiment with different combinations. The results show that focusing on the mouth increases the performance in small dataset settings while shifting the focus on the hands retrieves better results in larger dataset settings. Our results contribute to better accessibility for non-hearing persons by improving the systems powering digital assistants, enabling a more accurate interaction. The code for this project can be found on GitHub.