Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation
This work addresses performance enhancement for neural machine translation researchers, but it is incremental as SimCut is adapted from an existing method.
The paper tackles the problem of improving neural machine translation performance by introducing Bi-SimCut, a training strategy that combines bidirectional pretraining and unidirectional finetuning with a regularization method called SimCut, achieving BLEU scores such as 31.16 for en->de and 38.37 for de->en on the IWSLT14 dataset.
We introduce Bi-SimCut: a simple but effective training strategy to boost neural machine translation (NMT) performance. It consists of two procedures: bidirectional pretraining and unidirectional finetuning. Both procedures utilize SimCut, a simple regularization method that forces the consistency between the output distributions of the original and the cutoff sentence pairs. Without leveraging extra dataset via back-translation or integrating large-scale pretrained model, Bi-SimCut achieves strong translation performance across five translation benchmarks (data sizes range from 160K to 20.2M): BLEU scores of 31.16 for en -> de and 38.37 for de -> en on the IWSLT14 dataset, 30.78 for en -> de and 35.15 for de -> en on the WMT14 dataset, and 27.17 for zh -> en on the WMT17 dataset. SimCut is not a new method, but a version of Cutoff (Shen et al., 2020) simplified and adapted for NMT, and it could be considered as a perturbation-based method. Given the universality and simplicity of SimCut and Bi-SimCut, we believe they can serve as strong baselines for future NMT research.