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

Autor:	Gao, Pengzhi, He, Zhongjun, Wu, Hua, Wang, Haifeng
Rok vydání:	2022
Předmět:	Computer Science - Computation and Language Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: NAACL 2022 main conference
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2206.02368 Zobrazit plný text záznamu View this record from Arxiv