The code and models will be released soon.
If you find this repo helpful for your research, please cite:
@inproceedings{CeMAT,
author = {Li, Pengfei and Li, Liangyou and Zhang, Meng and Wu, Minghao and Liu, Qun},
title = {Universal Conditional Masked Language Pre-training for Neural Machine Translation},
booktitle = {Annual Meeting of the Association for Computational Linguistics},
year = {2022}
}