Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction
It addresses the problem of enabling machine translation for low-resource Indigenous languages, which is an incremental step in expanding NLP applications to underserved linguistic communities.
The paper introduces the challenges and techniques for developing neural machine translation systems for Indigenous languages of the Americas, which lack large training datasets, and discusses recent advances and open questions in this area.
Neural models have drastically advanced state of the art for machine translation (MT) between high-resource languages. Traditionally, these models rely on large amounts of training data, but many language pairs lack these resources. However, an important part of the languages in the world do not have this amount of data. Most languages from the Americas are among them, having a limited amount of parallel and monolingual data, if any. Here, we present an introduction to the interested reader to the basic challenges, concepts, and techniques that involve the creation of MT systems for these languages. Finally, we discuss the recent advances and findings and open questions, product of an increased interest of the NLP community in these languages.