: The performance of a statistical machine translation (SMT) system heavily depends on the quantity and quality of the bilingual language resource. However, the pervious work mainl...
: In this paper, we propose a new approach to improve the translation quality by adding the Key-Words of a sentence to the parallel corpus. The main idea of the approach is to find...
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...
This paper proposes a novel method for phrase-based statistical machine translation by using pivot language. To conduct translation between languages Lf and Le with a small biling...
In current phrase-based Statistical Machine Translation systems, more training data is generally better than less. However, a larger data set eventually introduces a larger model ...