For many years, statistical machine translation relied on generative models to provide bilingual word alignments. In 2005, several independent efforts showed that discriminative m...
Automatic error detection is desired in the post-processing to improve machine translation quality. The previous work is largely based on confidence estimation using system-based ...
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...
The pipeline of most Phrase-Based Statistical Machine Translation (PB-SMT) systems starts from automatically word aligned parallel corpus. But word appears to be too fine-grained ...
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 ...