Abstract
This paper describes DUTNLP Lab’s submission to the WMT22 General MT Task on four translation directions: English to/from Chinese and English to/from Japanese under the constrained condition.Our primary system are built on several Transformer variants which employ wider FFN layer or deeper encoder layer. The bilingual data are filtered by detailed data pre-processing strategies and four data augmentation methods are combined to enlarge the training data with the provided monolingual data.Several common methods are also employed to further improve the model performance, such as fine-tuning, model ensemble and post-editing.As a result, our constrained systems achieve 29.01, 63.87, 41.84, and 24.82 BLEU scores on Chinese-to-English, English-to-Chinese, English-to-Japanese, and Japanese-to-English, respectively.- Anthology ID:
- 2022.wmt-1.35
- Volume:
- Proceedings of the Seventh Conference on Machine Translation (WMT)
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates (Hybrid)
- Venue:
- WMT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 397–402
- Language:
- URL:
- https://aclanthology.org/2022.wmt-1.35
- DOI:
- Cite (ACL):
- Ting Wang, Huan Liu, Junpeng Liu, and Degen Huang. 2022. DUTNLP Machine Translation System for WMT22 General MT Task. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 397–402, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
- Cite (Informal):
- DUTNLP Machine Translation System for WMT22 General MT Task (Wang et al., WMT 2022)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2022.wmt-1.35.pdf