Hi, guys,
 I am using Moses to do a English to do a Chinese translation. And when I train
the data, and there are error as follows,
   where i think the these phrases are actually matched instead of mismatch.
   can you help me and tell me why and how to fix this? Thanks a lot.

.....
mismatch line 10: (% of ne % of || È« ne È«  || 0.333333 ne 0.125 || (0)
() ne
(0) () )
mismatch line 11: (% of ne % of || È« Ê¡ ne È« Ê¡  || 0.2 ne 0.125 || (0)
() ne
(0) () )
There were mismatches! (printed only first 10) at
bin/moses-scripts/scripts-20080603-0110/training/train-factored-phrase-model.perl
line
997.

my script is:
 
bin/moses-scripts/scripts-20080603-0110/training/train-factored-phrase-model.perl
 -scripts-root-dir bin/moses-scripts/scripts-20080603-0110/ -root-dir 
../../srilm/ -corpus ../corpus/test2 -f en -e ch -alignment grow-diag-final-and 
-reordering msd-bidirectional-fe -lm 0:5:../../srilm/lm/test2.lm:0

Can anyone help me figure out why? thanks a lot...


_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support

Reply via email to