Sign Language Sense Disambiguation
This work addresses accessibility for non-hearing persons by improving sign language translation systems, though it appears to be an incremental improvement using existing methods on new data.
This paper tackles the problem of homonym disambiguation in German sign language translation by training transformer models with different bodypart representations. The results show that focusing on mouth representations improves performance with small datasets, while hand representations work better with larger datasets.
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.