Why not just score them with a language model outside of the decoder?
Miles On Sep 24, 2011 3:38 PM, "Julian Myerscough" <[email protected]> wrote: > Hi folks, > > I would like to check newly translated sentences against an existing > language model to see how "likely" (or more importantly "unlikely") they > are (how well they fit into the existing model). > > Could you give me any pointers? > > Cheers > > Julian > > _______________________________________________ > 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
