Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges

TL;DR

This paper presents a large-scale multilingual neural machine translation system covering 103 languages, demonstrating transfer learning benefits and analyzing key challenges for universal translation.

Contribution

It introduces a massively multilingual NMT model trained on over 25 billion examples, showing effective transfer learning and detailed analysis of its capabilities and issues.

Findings

Improved translation quality for low-resource languages

High-resource language translation remains competitive

Identified challenges for universal NMT system development

Abstract

We introduce our efforts towards building a universal neural machine translation (NMT) system capable of translating between any language pair. We set a milestone towards this goal by building a single massively multilingual NMT model handling 103 languages trained on over 25 billion examples. Our system demonstrates effective transfer learning ability, significantly improving translation quality of low-resource languages, while keeping high-resource language translation quality on-par with competitive bilingual baselines. We provide in-depth analysis of various aspects of model building that are crucial to achieving quality and practicality in universal NMT. While we prototype a high-quality universal translation system, our extensive empirical analysis exposes issues that need to be further addressed, and we suggest directions for future research.