Previous methods on improving translation quality by employing multiple SMT models usually carry out as a secondpass decision procedure on hypotheses from multiple systems using e...
Syntactic word reordering is essential for translations across different grammar structures between syntactically distant languagepairs. In this paper, we propose to embed local a...
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 ...
A principal weakness of conventional (i.e., non-hierarchical) phrase-based statistical machine translation is that it can only exploit continuous phrases. In this paper, we extend...