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

• DOI: 10.18653/v1/2023.americasnlp-1.13
• Publication Date: 2023-08-05T00:57:42Z
• Authors: Manuel Mager; Rajat Bhatnagar; Graham Neubig; Ngoc Thang Vu; Katharina Kann
• Keywords: FOS: Computer and information sciences; Computer Science - Computation and Language; Statistics - Machine Learning; Machine Learning (stat.ML); Computation and Language (cs.CL)

Neural models have drastically advanced state of the art for machine translation (MT) between high-resource languages. Traditionally, these rely on large amounts training data, but many language pairs lack resources. However, an important part languages in world do not this amount data. Most from Americas are among them, having a limited parallel and monolingual if any. Here, we present introduction to interested reader basic challenges, concepts, techniques that involve creation MT systems Finally, discuss recent advances findings open questions, product increased interest NLP community