A Systematic Analysis of Vocabulary and BPE Settings for Optimal Fine-tuning of NMT: A Case Study of In-domain Translation

Understand

The effectiveness of Neural Machine Translation (NMT) models largely depends on the vocabulary used at training; small vocabularies can lead to out-of-vocabulary problems -- large ones, to memory issues.

• Subword (SW) tokenization has been successfully employed to mitigate these issues.
• The choice of vocabulary and SW tokenization has a significant impact on both training and fine-tuning an NMT model.
• Fine-tuning is a common practice in optimizing an MT model with respect to new data.