Unsmoothed Maximum-Likelihood Training Algorithm
Jump to navigation
Jump to search
An Unsmoothed Maximum-Likelihood Training Algorithm is a Maximum-Likelihood Training Algorithm that ...
- See: Smoothed Maximum-Likelihood Training Algorithm, Maximum-Likelihood Language Model, Language Model Training Algorithm.
References
2003
- (Och, 2003) ⇒ Franz Josef Och. (2003). “Minimum Error Rate Training in Statistical Machine Translation.” In: Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1. doi:10.3115/1075096.1075117
- QUOTE: Often, the training procedure for statistical machine translation models is based on maximum likelihood or related criteria. A general problem of this approach is that there is only a loose relation to the final translation quality on unseen text.