1. Paper title
Improving Non-autoregressive Neural Machine Translation with Monolingual Data
2. link
https://www.aclweb.org/anthology/2020.acl-main.171.pdf
3. 摘要
Non-autoregressive (NAR) neural machine translation is usually done via knowledge distillation from an autoregressive (AR) model. Under this framework, we leverage large monolingual corpora to improve the NAR model’s performance, with the goal of transferring the AR model’s generalization ability while preventing overfitting. On top of a strong NAR baseline, our experimental results on the WMT14 En-De and WMT16 En-Ro news translation tasks confirm that monolingual data augmentation consistently improves the performance of the NAR model to approach the teacher AR model’s performance, yields comparable or better results than the best non-iterative NAR methods in the literature and helps reduce overfitting in the training process.
monolingual corpora：单语语料库
4. 要解决什么问题
？
5. 作者的主要贡献
利用大型单语语料库来提高NAR模型的性能，目的是转移AR模型的泛化能力，同时防止过度拟合
6. 得到了什么结果
WMT14 En-De and WMT16 En-Ro
提升了性能，减少overfitting