Modeling Fluency and Faithfulness for Diverse Neural Machine Translation


  • Yang Feng Chinese Academy of Sciences
  • Wanying Xie Beijing Language and Culture University
  • Shuhao Gu Chinese Academy of Sciences
  • Chenze Shao Chinese Academy of Sciences
  • Wen Zhang Tencent
  • Zhengxin Yang Chinese Academy of Sciences
  • Dong Yu Beijing Language and Culture University



Neural machine translation models usually adopt the teacher forcing strategy for training which requires the predicted sequence matches ground truth word by word and forces the probability of each prediction to approach a 0-1 distribution. However, the strategy casts all the portion of the distribution to the ground truth word and ignores other words in the target vocabulary even when the ground truth word cannot dominate the distribution. To address the problem of teacher forcing, we propose a method to introduce an evaluation module to guide the distribution of the prediction. The evaluation module accesses each prediction from the perspectives of fluency and faithfulness to encourage the model to generate the word which has a fluent connection with its past and future translation and meanwhile tends to form a translation equivalent in meaning to the source. The experiments on multiple translation tasks show that our method can achieve significant improvements over strong baselines.




How to Cite

Feng, Y., Xie, W., Gu, S., Shao, C., Zhang, W., Yang, Z., & Yu, D. (2020). Modeling Fluency and Faithfulness for Diverse Neural Machine Translation . Proceedings of the AAAI Conference on Artificial Intelligence, 34(01), 59-66.



AAAI Technical Track: AI and the Web