Abstract
This paper describes Lan-Bridge Translation systems for the WMT 2022 General Translation shared task. We participate in 18 language directions: English to and from Czech, German, Ukrainian, Japanese, Russian, Chinese, English to Croatian, French to German, Yakut to and from Russian and Ukrainian to and from Czech.To develop systems covering all these direc_x0002_tions, we mainly focus on multilingual mod_x0002_els. In general, we apply data corpus filtering, scaling model size, sparse expert model (in par_x0002_ticular, Transformer with adapters), large scale backtranslation and language model rerankingtechniques. Our system ranks first in 6 directions based on automatic evaluation.- Anthology ID:
- 2022.wmt-1.19
- 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:
- 268–274
- Language:
- URL:
- https://aclanthology.org/2022.wmt-1.19
- DOI:
- Cite (ACL):
- Bing Han, Yangjian Wu, Gang Hu, and Qiulin Chen. 2022. Lan-Bridge MT’s Participation in the WMT 2022 General Translation Shared Task. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 268–274, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
- Cite (Informal):
- Lan-Bridge MT’s Participation in the WMT 2022 General Translation Shared Task (Han et al., WMT 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.wmt-1.19.pdf