Hi, these ranges are just for the random initialization. The optimized weights may be anything.
-phi 2012/3/15 Kun Wang <[email protected]>: > Hi, all, > > When I use mert-moses.pl, the weight range of one feature is from 0.0 to > 1.0, why the final weight for this feature I got is below 0? > Does anyone know how to solve this problem? Or how to make the final weights > with mert are in the right ranges as expected? Thanks a lot in advance. > > Best regards, > Kun Wang > > 2012-03-15 > ========================================================= > 汪昆 Wang Kun > National Laboratory of Pattern Recognition (NLPR) > Institute of Automation, Chinese Academy of Sciences > Beijing，China > Tel：8610 82614468 > Email: [email protected] or [email protected] > ========================================================= > > _______________________________________________ > 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
