Abstract
We present a simple yet powerful data augmentation method for boosting Neural Machine Translation (NMT) performance by
leveraging information retrieved from a Translation Memory (TM). We propose and test two
methods for augmenting NMT training data
with fuzzy TM matches. Tests on the DGTTM data set for two language pairs show consistent and substantial improvements over a
range of baseline systems. The results suggest
that this method is promising for any translation environment in which a sizeable TM is
available and a certain amount of repetition
across translations is to be expected, especially
considering its ease of implementation