@InProceedings{zhang-EtAl:2018:EMNLP12,
  author    = {Zhang, Wen  and  Huang, Liang  and  Feng, Yang  and  Shen, Lei  and  Liu, Qun},
  title     = {Speeding Up Neural Machine Translation Decoding by Cube Pruning},
  booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing},
  month     = {October-November},
  year      = {2018},
  address   = {Brussels, Belgium},
  publisher = {Association for Computational Linguistics},
  pages     = {4284--4294},
  url       = {http://www.aclweb.org/anthology/D18-1460}
}