Minimum Risk Training for Neural Machine Translation
2016pp. 1683–1692
Citations Over TimeTop 1% of 2016 papers
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 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.
Related Papers
- → A Characterization for Generalized Hukuhara Differentiable Interval-Valued Functions and Some Rules of Calculus(2022)2 cited
- → Continuous Differentiability in the Context of Generalized Approach to Differentiability(2023)1 cited
- → The Complexity Of Nowhere Differentiable Continuous Functions(1989)1 cited
- On binary function continuity,differentiability and may differentiability(2012)
- → On derivatives of fuzzy multi-dimensional mappings and applications under generalized differentiability(2021)