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 ende and 38.37 for deen on the IWSLT14 dataset, 30.78 for ende and 35.15 for deen on the WMT14 dataset, and 27.17 for zhen 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
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
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://preview.aclanthology.org/landing_page/2022.naacl-main.289.pdf
Video:
 https://preview.aclanthology.org/landing_page/2022.naacl-main.289.mp4
Code
 gpengzhi/Bi-SimCut
Data
WMT 2014