DiDi’s Machine Translation System for WMT2020
Tanfang Chen, Weiwei Wang, Wenyang Wei, Xing Shi, Xiangang Li, Jieping Ye, Kevin Knight
Abstract
This paper describes the DiDi AI Labs’ submission to the WMT2020 news translation shared task. We participate in the translation direction of Chinese->English. In this direction, we use the Transformer as our baseline model and integrate several techniques for model enhancement, including data filtering, data selection, back-translation, fine-tuning, model ensembling, and re-ranking. As a result, our submission achieves a BLEU score of 36.6 in Chinese->English.- Anthology ID:
- 2020.wmt-1.7
- Volume:
- Proceedings of the Fifth Conference on Machine Translation
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 105–112
- Language:
- URL:
- https://aclanthology.org/2020.wmt-1.7
- DOI:
- Cite (ACL):
- Tanfang Chen, Weiwei Wang, Wenyang Wei, Xing Shi, Xiangang Li, Jieping Ye, and Kevin Knight. 2020. DiDi’s Machine Translation System for WMT2020. In Proceedings of the Fifth Conference on Machine Translation, pages 105–112, Online. Association for Computational Linguistics.
- Cite (Informal):
- DiDi’s Machine Translation System for WMT2020 (Chen et al., WMT 2020)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2020.wmt-1.7.pdf