@inproceedings{gao-etal-2022-bi,
    title = "{B}i-{S}im{C}ut: A Simple Strategy for Boosting Neural Machine Translation",
    author = "Gao, Pengzhi  and
      He, Zhongjun  and
      Wu, Hua  and
      Wang, Haifeng",
    editor = "Carpuat, Marine  and
      de Marneffe, Marie-Catherine  and
      Meza Ruiz, Ivan Vladimir",
    booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2022.naacl-main.289/",
    doi = "10.18653/v1/2022.naacl-main.289",
    pages = "3938--3948",
    abstract = "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 $\texttt{en}\rightarrow\texttt{de}$ and 38.37 for $\texttt{de}\rightarrow\texttt{en}$ on the IWSLT14 dataset, 30.78 for $\texttt{en}\rightarrow\texttt{de}$ and 35.15 for $\texttt{de}\rightarrow\texttt{en}$ on the WMT14 dataset, and 27.17 for $\texttt{zh}\rightarrow\texttt{en}$ 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 Bi-SimCut and SimCut, we believe they can serve as strong baselines for future NMT research."
}