%0 Conference Proceedings %T The NiuTrans Machine Translation Systems for WMT19 %A Li, Bei %A Li, Yinqiao %A Xu, Chen %A Lin, Ye %A Liu, Jiqiang %A Liu, Hui %A Wang, Ziyang %A Zhang, Yuhao %A Xu, Nuo %A Wang, Zeyang %A Feng, Kai %A Chen, Hexuan %A Liu, Tengbo %A Li, Yanyang %A Wang, Qiang %A Xiao, Tong %A Zhu, Jingbo %Y Bojar, Ondřej %Y Chatterjee, Rajen %Y Federmann, Christian %Y Fishel, Mark %Y Graham, Yvette %Y Haddow, Barry %Y Huck, Matthias %Y Yepes, Antonio Jimeno %Y Koehn, Philipp %Y Martins, André %Y Monz, Christof %Y Negri, Matteo %Y Névéol, Aurélie %Y Neves, Mariana %Y Post, Matt %Y Turchi, Marco %Y Verspoor, Karin %S Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1) %D 2019 %8 August %I Association for Computational Linguistics %C Florence, Italy %F li-etal-2019-niutrans %X This paper described NiuTrans neural machine translation systems for the WMT 2019 news translation tasks. We participated in 13 translation directions, including 11 supervised tasks, namely EN↔ZH, DE, RU, KK, LT, GU→EN and the unsupervised DE↔CS sub-track. Our systems were built on Deep Transformer and several back-translation methods. Iterative knowledge distillation and ensemble+reranking were also employed to obtain stronger models. Our unsupervised submissions were based on NMT enhanced by SMT. As a result, we achieved the highest BLEU scores in KK↔EN, GU→EN directions, ranking 2nd in RU→EN, DE↔CS and 3rd in ZH→EN, LT→EN, EN→RU, EN↔DE among all constrained submissions. %R 10.18653/v1/W19-5325 %U https://aclanthology.org/W19-5325 %U https://doi.org/10.18653/v1/W19-5325 %P 257-266