Bayesian approaches have been shown to reduce the amount of overfitting that occurs when running the EM algorithm, by placing prior probabilities on the model parameters. We appl...
The dominant practice of statistical machine translation (SMT) uses the same Chinese word segmentation specification in both alignment and translation rule induction steps in buil...
Ning Xi, Guangchao Tang, Xinyu Dai, Shujian Huang,...
This paper considers a scenario when we are given almost perfect knowledge about bilingual terminology in terms of a test corpus in Statistical Machine Translation (SMT). When the...
HMM-based models are developed for the alignment of words and phrases in bitext. The models are formulated so that alignment and parameter estimation can be performed efficiently....