Hi Ambaye

> BLEU = 0.00, 0.0/0.0/0.0/0.0 (BP=0.000, ratio=0.002, hyp_len=48307,
> ref_len=19888011)

Why is the reference length much longer than the hypothesis length?  
Are you comparing the right files?

cheers - Barry

Quoting Ambaye Tadesse <[email protected]> on Fri, 8 Jun 2012  
13:54:01 +0300:

> dear moses team,
> when I try to evaluate the hierarchical model like this, i face problem,
>
>  ./multi-bleu.perl work/evaluation/amharicTs.tok.txt <
> work/evaluation/englishTs.tuned.output.tok.txt
> Use of uninitialized value in division (/) at ./multi-bleu.perl line 114,
> <STDIN> line 1989.
> Use of uninitialized value in division (/) at ./multi-bleu.perl line 114,
> <STDIN> line 1989.
> Use of uninitialized value in division (/) at ./multi-bleu.perl line 114,
> <STDIN> line 1989.
> Use of uninitialized value in division (/) at ./multi-bleu.perl line 114,
> <STDIN> line 1989.
> BLEU = 0.00, 0.0/0.0/0.0/0.0 (BP=0.000, ratio=0.002, hyp_len=48307,
> ref_len=19888011)
>
> would you mind to solve this problem?
>
> Thanks with Regards
> Ambaye
>



-- 
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.


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

Reply via email to