Abstract
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.- Anthology ID:
- 2021.wmt-1.108
- Volume:
- Proceedings of the Sixth Conference on Machine Translation
- Month:
- November
- Year:
- 2021
- Address:
- Online
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1009–1013
- Language:
- URL:
- https://aclanthology.org/2021.wmt-1.108
- DOI:
- Cite (ACL):
- Meng Zhang, Minghao Wu, Pengfei Li, Liangyou Li, and Qun Liu. 2021. NoahNMT at WMT 2021: Dual Transfer for Very Low Resource Supervised Machine Translation. In Proceedings of the Sixth Conference on Machine Translation, pages 1009–1013, Online. Association for Computational Linguistics.
- Cite (Informal):
- NoahNMT at WMT 2021: Dual Transfer for Very Low Resource Supervised Machine Translation (Zhang et al., WMT 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.wmt-1.108.pdf