@inproceedings{lam-etal-2018-reinforcement,
    title = "A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation",
    author = "Lam, Tsz Kin  and
      Kreutzer, Julia  and
      Riezler, Stefan",
    editor = "P{\'e}rez-Ortiz, Juan Antonio  and
      S{\'a}nchez-Mart{\'i}nez, Felipe  and
      Espl{\`a}-Gomis, Miquel  and
      Popovi{\'c}, Maja  and
      Rico, Celia  and
      Martins, Andr{\'e}  and
      Van den Bogaert, Joachim  and
      Forcada, Mikel L.",
    booktitle = "Proceedings of the 21st Annual Conference of the European Association for Machine Translation",
    month = may,
    year = "2018",
    address = "Alicante, Spain",
    url = "https://preview.aclanthology.org/ingest-emnlp/2018.eamt-main.17/",
    pages = "189--198",
    abstract = "We present an approach to interactivepredictive neural machine translation that attempts to reduce human effort from three directions: Firstly, instead of requiring humans to select, correct, or delete segments, we employ the idea of learning from human reinforcements in form of judgments on the quality of partial translations. Secondly, human effort is further reduced by using the entropy of word predictions as uncertainty criterion to trigger feedback requests. Lastly, online updates of the model parameters after every interaction allow the model to adapt quickly. We show in simulation experiments that reward signals on partial translations significantly improve character F-score and BLEU compared to feedback on full translations only, while human effort can be reduced to an average number of 5 feedback requests for every input."
}