Theorizing sustainable, low-resource MT in development settings

Abstract

Abstract This article conducts a meta-analysis of existing research to theorize how machine translation (MT) may help resolve underlying contradictions in the development sector that preclude the UN’s 10th Sustainable Development Goal: to reduce inequality within and among countries. Non-governmental organizations (NGOs) frequently work in dominant languages and neglect marginalized languages, reinforcing power imbalances between the Global North and Global South in development planning. MT between marginalized languages may improve collaboration between local communities to redress shared disadvantages. As an example, the article hypothesizes a sustainable, “low-tech” MT system pivoting through Spanish to translate between three Mayan languages in Guatemala: K’iche’, Q’eqchi’, and Mam. First, the article theorizes three key dimensions comprising the overall sustainability of low-resource MT in development: quality, social, and environmental. It then evaluates the sustainability of various MT architectures. Finally, it reaffirms the ability for indirect translation (classic pivot-based MT) to facilitate MT between low-resource languages.