Hi, there is currently no straightforward way to do this.
You could generate a very large n-best list and then filter it for reordering diversity, either within the decoder or outside of it. -phi On Sat, Sep 7, 2013 at 10:26 AM, Saeed Farzi <[email protected]> wrote: > Hi members, > > how to make moses to generate n-best lists which contain the hypotheses > with so different reordering . > tnx in advance, > > -- > S.Farzi, Ph.D. Student > Natural Language Processing Lab, > School of Electrical and Computer Eng., > Tehran University > Tel: +9821-6111-9719 > > > _______________________________________________ > 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
