Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction

TL;DR

This paper introduces the challenges and recent progress in developing neural machine translation systems for indigenous American languages, which lack large datasets, highlighting the need for tailored approaches.

Contribution

It provides an overview of the specific challenges, concepts, and techniques for MT in low-resource indigenous languages of the Americas, and discusses recent advances and open questions.

Findings

Increased NLP community interest in indigenous languages.

Recent advances in low-resource MT techniques.

Open research questions remain in this area.

Abstract

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.