Considerations for meaningful sign language machine translation based on glosses
This work highlights critical methodological and evaluation problems in sign language translation research, aiming to improve future studies for better accessibility tools.
The paper identifies that gloss-based sign language machine translation research lacks transparency about gloss limitations, dataset issues, and standardized evaluation, and proposes recommendations to address these gaps.
Automatic sign language processing is gaining popularity in Natural Language Processing (NLP) research (Yin et al., 2021). In machine translation (MT) in particular, sign language translation based on glosses is a prominent approach. In this paper, we review recent works on neural gloss translation. We find that limitations of glosses in general and limitations of specific datasets are not discussed in a transparent manner and that there is no common standard for evaluation. To address these issues, we put forward concrete recommendations for future research on gloss translation. Our suggestions advocate awareness of the inherent limitations of gloss-based approaches, realistic datasets, stronger baselines and convincing evaluation.