Language Justice and Machine Translation on Social Media

Machine translation (MT), which involves the use of algorithms to translate between languages, has advanced to a high level of quality for dozens of language pairs and is employed in an array of everyday contexts, including on social media. However, there are hundreds of languages for which there are insufficient digital resources to sustain quality machine translation, and errors abound even in translations for so-called “high-resource” language pairs. Meanwhile, although decades of research have led to improvements in MT system performance, recent scholarship has drawn attention to the social impact of MT systems. The present article builds on this burgeoning tradition and advocates for a language justice orientation in MT system development and design, focusing on online social media as a case study. This view advocates for transparency and consent in the application of machine translation. We also consider how language justice can inform the management of linguistic resources used to train MT systems.