We address the problem of extracting bilingual chunk pairs from parallel text to create training sets for statistical machine translation. We formulate the problem in terms of a s...
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,...
Automatic word alignment is a key step in training statistical machine translation systems. Despite much recent work on word alignment methods, alignment accuracy increases often ...
We introduce a semi-supervised approach to training for statistical machine translation that alternates the traditional Expectation Maximization step that is applied on a large tr...