Hi, there is a whole line of research that does rule-based reordering based on syntactic analysis before passing on reordered input to the statistical machine translation pipeline.
Take a look at this paper and the follow-up work: http://scholar.google.com/scholar?cluster=7772004091347723084&hl=en&as_sdt=0,5 -phi On Sat, Jun 9, 2012 at 3:33 PM, Ambaye Tadesse <[email protected]> wrote: > dear, > my hierarchal translation is poor in reordering, i want to develope a module > that tags the source side(English which is SVO) and reorder the verb like > target side(Amharic which is SOV) before decoding engine starts. > any one who helps doing this process developing a module and combining with > translation model? > > Thanks with best Regards > Ambaye. > > _______________________________________________ > Moses-support mailing list > [email protected] > http://mailman.mit.edu/mailman/listinfo/moses-support > _______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
