Minimum Risk Training for Neural Machine Translation
meeting of the association for computational linguistics, pp. 1683-1692, 2016.
EI
Abstract:
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 arbitrary evaluation metrics, which are not necessarily differentiable. Experiments show that our approach achieves signif...More
Code:
Data:
Tags
Comments