%0 Conference Proceedings %T Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation %A Gao, Pengzhi %A He, Zhongjun %A Wu, Hua %A Wang, Haifeng %Y Carpuat, Marine %Y de Marneffe, Marie-Catherine %Y Meza Ruiz, Ivan Vladimir %S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies %D 2022 %8 July %I Association for Computational Linguistics %C Seattle, United States %F gao-etal-2022-bi %X 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\rightarrowde and 38.37 for de\rightarrowen on the IWSLT14 dataset, 30.78 for en\rightarrowde and 35.15 for de\rightarrowen on the WMT14 dataset, and 27.17 for zh\rightarrowen 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 Bi-SimCut and SimCut, we believe they can serve as strong baselines for future NMT research. %R 10.18653/v1/2022.naacl-main.289 %U https://aclanthology.org/2022.naacl-main.289 %U https://doi.org/10.18653/v1/2022.naacl-main.289 %P 3938-3948