-- 




Thanks Loic,
One more question:
The individual 1, 2, 3, and 4 -gram BLEU scores are computed by
dividing by a total of ngrams.
>From reading the multi-bleu.perl code the total comes from the ngrams
in the hypothesis.
Is this what you want?
Shouldn't the total be computed over the references?
John
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support

Reply via email to