@inproceedings{hu-etal-2018-tencentfmrd,
    title = "{T}encent{F}m{RD} Neural Machine Translation for {WMT}18",
    author = "Hu, Bojie  and
      Han, Ambyer  and
      Huang, Shen",
    editor = "Bojar, Ond{\v{r}}ej  and
      Chatterjee, Rajen  and
      Federmann, Christian  and
      Fishel, Mark  and
      Graham, Yvette  and
      Haddow, Barry  and
      Huck, Matthias  and
      Yepes, Antonio Jimeno  and
      Koehn, Philipp  and
      Monz, Christof  and
      Negri, Matteo  and
      N{\'e}v{\'e}ol, Aur{\'e}lie  and
      Neves, Mariana  and
      Post, Matt  and
      Specia, Lucia  and
      Turchi, Marco  and
      Verspoor, Karin",
    booktitle = "Proceedings of the Third Conference on Machine Translation: Shared Task Papers",
    month = oct,
    year = "2018",
    address = "Belgium, Brussels",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/W18-6413/",
    doi = "10.18653/v1/W18-6413",
    pages = "410--417",
    abstract = "This paper describes the Neural Machine Translation (NMT) system of TencentFmRD for Chinese{\ensuremath{\leftrightarrow}}English news translation tasks of WMT 2018. Our systems are neural machine translation systems trained with our original system TenTrans. TenTrans is an improved NMT system based on Transformer self-attention mechanism. In addition to the basic settings of Transformer training, TenTrans uses multi-model fusion techniques, multiple features reranking, different segmentation models and joint learning. Finally, we adopt some data selection strategies to fine-tune the trained system and achieve a stable performance improvement. Our Chinese{\textrightarrow}English system achieved the second best BLEU scores and fourth best cased BLEU scores among all WMT18 submitted systems."
}