Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation

Pengzhi Gao, Zhongjun He, Hua Wu, Haifeng Wang


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}\texttt{de} and 38.37 for \texttt{de}\texttt{en} on the IWSLT14 dataset, 30.78 for \texttt{en}\texttt{de} and 35.15 for \texttt{de}\texttt{en} on the WMT14 dataset, and 27.17 for \texttt{zh}\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.
Anthology ID:
2022.naacl-main.289
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3938–3948
Language:
URL:
https://aclanthology.org/2022.naacl-main.289
DOI:
10.18653/v1/2022.naacl-main.289
Bibkey:
Cite (ACL):
Pengzhi Gao, Zhongjun He, Hua Wu, and Haifeng Wang. 2022. Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3938–3948, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation (Gao et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.289.pdf
Code
 gpengzhi/Bi-SimCut
Data
WMT 2014