EASIER project partners received an outstanding paper award for research on sign language translation at the 61st Annual Meeting of the Association for Computational Linguistics (ACL’23). The paper titled, “Considerations for meaningful sign language machine translation based on glosses*” provides a critical view of machine translation research involving sign language glosses, with recommendations for the ideal methodology of future experiments. Congratulation to the authors, Mathias Müller, Zifan Jiang, Amit Moryossef, Annette Rios, and Sarah Ebling.
Abstract
Automatic sign language processing is gaining popularity in Natural Language Processing (NLP) research (Yinetal.,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 data sets 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.
About ACL
The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing (NLP). The association was founded in 1962, originally named the Association for Machine Translation and Computational Linguistics (AMTCL) and became the ACL in 1968. Activities of the ACL include the holding of an annual meeting each summer and the sponsoring of the journal Computational Linguistics, published by MIT Press; this conference and journal are the leading publications of the field. The 61st Annual Meeting of the Association took place in Toronto, Canada on July 9-14, 2023.
*The paper was funded by EASIER and IICT.