NoahNMT at WMT 2021: Dual Transfer for Very Low Resource Supervised Machine Translation
2021-11-01WMT (EMNLP) 2021Unverified0· sign in to hype
Meng Zhang, Minghao Wu, Pengfei Li, Liangyou Li, Qun Liu
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
This paper describes the NoahNMT system submitted to the WMT 2021 shared task of Very Low Resource Supervised Machine Translation. The system is a standard Transformer model equipped with our recent technique of dual transfer. It also employs widely used techniques that are known to be helpful for neural machine translation, including iterative back-translation, selected finetuning, and ensemble. The final submission achieves the top BLEU for three translation directions.