Title: A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation

Abstract:
We present an approach to interactive-predictive 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.