NoahNMT at WMT 2021: Dual Transfer for Very Low Resource Supervised Machine Translation


Abstract in English

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.

References used

https://aclanthology.org/

Download