Revisiting Low-Resource Neural Machine Translation: A Case Study

TL;DR

This paper reevaluates low-resource neural machine translation, demonstrating that with proper system adaptation and optimization, NMT can outperform traditional methods even with limited data, challenging prior assumptions.

Contribution

It highlights the importance of system adaptation and best practices in low-resource NMT, showing improved results without auxiliary data.

Findings

Optimized NMT outperforms PBSMT with less data.

Techniques improve BLEU scores in low-resource settings.

Proper adaptation can close the performance gap in low-resource NMT.

Abstract

It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions, underperforming phrase-based statistical machine translation (PBSMT) and requiring large amounts of auxiliary data to achieve competitive results. In this paper, we re-assess the validity of these results, arguing that they are the result of lack of system adaptation to low-resource settings. We discuss some pitfalls to be aware of when training low-resource NMT systems, and recent techniques that have shown to be especially helpful in low-resource settings, resulting in a set of best practices for low-resource NMT. In our experiments on German--English with different amounts of IWSLT14 training data, we show that, without the use of any auxiliary monolingual or multilingual data, an optimized NMT system can outperform PBSMT with far less data than previously claimed. We also apply these techniques to a low-resource Korean-English dataset, surpassing previously reported results by 4 BLEU.