Abstract
In this paper we introduce the systems IIE submitted for the WMT20 shared task on German↔French news translation. Our systems are based on the Transformer architecture with some effective improvements. Multiscale collaborative deep architecture, data selection, back translation, knowledge distillation, domain adaptation, model ensemble and re-ranking are employed and proven effective in our experiments. Our German→French system achieved 35.0 BLEU and ranked the second among all anonymous submissions, and our French→German system achieved 36.6 BLEU and ranked the fourth in all anonymous submissions.
Cite
CITATION STYLE
Wei, X., Guo, P., Li, Y., Zhang, X., Xing, L., & Hu, Y. (2020). IIE’s Neural Machine Translation Systems for WMT20. In 5th Conference on Machine Translation, WMT 2020 - Proceedings (pp. 300–304). Association for Computational Linguistics (ACL).
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
