Papers › Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation
Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation
Pengzhi Gao, Zhongjun He, Hua Wu, Haifeng Wang
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 SimCut and Bi-SimCut, we believe they can serve as strong baselines for future NMT research.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Machine Translation | IWSLT2014 English-German | Bi-SimCut | BLEU score | 31.16 | #2 of 6 | Archive leaderboard | report |
| Machine Translation | IWSLT2014 English-German | SimCut | BLEU score | 30.98 | #3 of 6 | Archive leaderboard | report |
| Machine Translation | IWSLT2014 German-English | Bi-SimCut | BLEU score | 38.37 | #3 of 34 | Archive leaderboard | report |
| Machine Translation | IWSLT2014 German-English | SimCut | BLEU score | 37.81 | #7 of 34 | Archive leaderboard | report |
| Machine Translation | WMT2014 English-German | Bi-SimCut | BLEU score | 30.78 | #7 of 91 | Archive leaderboard | report |
| Machine Translation | WMT2014 English-German | SimCut | BLEU score | 30.56 | #10 of 91 | Archive leaderboard | report |
| Machine Translation | WMT2014 German-English | Bi-SimCut | BLEU score | 35.15 | #1 of 16 | Archive leaderboard | report |
| Machine Translation | WMT2014 German-English | SimCut | BLEU score | 34.86 | #3 of 16 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections