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 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 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
- 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)
- PDF:
- https://preview.aclanthology.org/landing_page/2022.naacl-main.289.pdf
- Code
- gpengzhi/Bi-SimCut
- Data
- WMT 2014