Minimum Risk Training for Neural Machine Translation

Understand

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 significant improvements over maximum likelihood estimation on a state-of-the-art neural machine translation system across various languages pairs.
• Transparent to architectures, our approach can be applied to more neural networks and potentially benefit more NLP tasks.