when you use
-tt
the decoder outputs the segmentation and the score from each feature
function. If you just want the plain output don't use this option.
For your example
between 1998 and 2000 "|0-4,wa=,total=-6.00208, SRILM0= -17.297
Distortion0= 0 LexicalReordering0= -1.94591 0 0 0 0 0 WordPenalty0= -4 "
1. between 1998 and 2000
- the target oytput
2. 0-4
- the source range that was translated
3. wa=
- i guess this is word alignment
4. total=-6.00208
- the total score
5. SRILM0= -17.297
- the score for the language model
And so on
On 23/02/2014 01:24, nadeem khan wrote:
> -print-alignment-info -
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support
