If you mean that you trained twice, it's normal to get slightly different
results. The word alignment and running are stocastic
On Sun, Mar 29, 2020, 3:49 AM rmogla wrote:
> Hi,
> I ran Moses baseline method twice with the same settings and with the same
> data set, but final translation file generated in both the cases is
> different.
>
> If i am doing something wrong please suggest?
> Thanks and regards
> ___
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
>
___
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
