How It Started and How It’s Going: Sign Language Machine Translation and Engagement with Deaf Communities Over the Past 25 Years
Temas
Detalles
This chapter explores the historical timeline of approaches to Sign Language Machine Translation (MT) over the past 25 years. Initially, such approaches were rule-based, but given advances in corpus-based approaches to MT on spoken languages, unsurprisingly researchers started to explore the possibilities for using example-based and statistical methods for sign languages. Then, as now, data sparseness was the main inhibitor to progress, but it is interesting to see to what extent this research engaged with deaf and hard of hearing (DHH) people in identifying use-cases, creating training data, and evaluating the translations as well as the overall process. We end with a description of the Horizon Europe-funded SignON project, focusing particularly on the co-constructed approach to identification and evaluation of use-cases with and by deaf signers that has been adopted. As can be seen throughout this volume (but especially in chapters “The Importance of Including Signed Languages in Natural Language Processing” and “Sign Language Machine Translation Communication and Engagement”), we contend most strongly that this is the only ethical approach to such work.
En A. Way, L. Leeson y D. Shterionov (Eds.), Sign language machine translation (pp. 27-72).