Revisiting Low-Resource Neural Machine Translation: A Case Study
This work addresses the challenge of low-resource machine translation for researchers and practitioners, offering incremental improvements through best practices.
The paper tackles the problem of neural machine translation underperforming in low-resource conditions by optimizing system adaptation, showing that an optimized NMT system can outperform phrase-based statistical machine translation with less data than previously claimed, achieving a 4 BLEU improvement on a Korean-English dataset.
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.