Abstract:
In statistical machine translation,
reordering is crucial component for translation of the
different languages with different word orders.
Without reordering during language translation,
sentences can only be translated properly into a
language with similar word order. An effective
reordering scheme is essential to model translation
between languages with different word orders, such
as SVO-languages (English or Chinese) and SOVlanguages
(Japanese or Turkish or Myanmar). In this
paper, we focus on reorder scheme for lexical
reordering to incorporate into our translation model.
If a sentence is given, our proposed reordering
system performs three tasks on this sentence such as
word level reordering, chunk level reordering and
clause level reordering. In this research, Markov
based Reordering Model will be implemented.
Moreover, the movement parameters to input the
reordering model are taken from the rules
automatically generated from parallel aligned
corpus.
