Dictionary-based Data Augmentation for Cross-Domain Neural Machine Translation
This addresses the issue of translation errors for low-frequency and out-of-vocabulary terminology in cross-domain NMT, offering an incremental improvement over existing methods like back-translation.
The paper tackles the problem of domain information gaps in neural machine translation by proposing a dictionary-based data augmentation method that synthesizes domain-specific dictionaries with general corpora to generate pseudo-in-domain data, resulting in improvements of 3.75-11.53 BLEU over baseline models.
Existing data augmentation approaches for neural machine translation (NMT) have predominantly relied on back-translating in-domain (IND) monolingual corpora. These methods suffer from issues associated with a domain information gap, which leads to translation errors for low frequency and out-of-vocabulary terminology. This paper proposes a dictionary-based data augmentation (DDA) method for cross-domain NMT. DDA synthesizes a domain-specific dictionary with general domain corpora to automatically generate a large-scale pseudo-IND parallel corpus. The generated pseudo-IND data can be used to enhance a general domain trained baseline. The experiments show that the DDA-enhanced NMT models demonstrate consistent significant improvements, outperforming the baseline models by 3.75-11.53 BLEU. The proposed method is also able to further improve the performance of the back-translation based and IND-finetuned NMT models. The improvement is associated with the enhanced domain coverage produced by DDA.