%0 Journal Article
%T Minimum Risk Training for Neural Machine Translation
%A Shiqi Shen
%A Yong Cheng
%A Zhongjun He
%A Wei He
%A Hua Wu
%A Maosong Sun
%A Yang Liu
%J Computer Science
%D 2015
%I arXiv
%X We propose minimum risk training for end-to-end neural machine translation. Unlike conventional maximum likelihood estimation, minimum risk training is capable of optimizing model parameters directly with respect to evaluation metrics. Experiments on Chinese-English and English-French translation show that our approach achieves significant improvements over maximum likelihood estimation on a state-of-the-art neural machine translation system.
%U http://arxiv.org/abs/1512.02433v2