The NiuTrans Machine Translation System for WMT18
Qiang Wang, Bei Li, Jiqiang Liu, Bojian Jiang, Zheyang Zhang, Yinqiao Li, Ye Lin, Tong Xiao, Jingbo Zhu
Abstract
This paper describes the submission of the NiuTrans neural machine translation system for the WMT 2018 Chinese ↔ English news translation tasks. Our baseline systems are based on the Transformer architecture. We further improve the translation performance 2.4-2.6 BLEU points from four aspects, including architectural improvements, diverse ensemble decoding, reranking, and post-processing. Among constrained submissions, we rank 2nd out of 16 submitted systems on Chinese → English task and 3rd out of 16 on English → Chinese task, respectively.- Anthology ID:
- W18-6430
- Volume:
- Proceedings of the Third Conference on Machine Translation: Shared Task Papers
- Month:
- October
- Year:
- 2018
- Address:
- Belgium, Brussels
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 528–534
- Language:
- URL:
- https://aclanthology.org/W18-6430
- DOI:
- 10.18653/v1/W18-6430
- Cite (ACL):
- Qiang Wang, Bei Li, Jiqiang Liu, Bojian Jiang, Zheyang Zhang, Yinqiao Li, Ye Lin, Tong Xiao, and Jingbo Zhu. 2018. The NiuTrans Machine Translation System for WMT18. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 528–534, Belgium, Brussels. Association for Computational Linguistics.
- Cite (Informal):
- The NiuTrans Machine Translation System for WMT18 (Wang et al., WMT 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/W18-6430.pdf