Hi Mailing list,
I have some problems while training parallel corpus (48MB corpus). I have
seen GIZA has found this error :
 > Hmm: Iteration 5
> Reading more sentence pairs into memory ...
...
>  ERROR: nan nan nan 52 38
> ERROR: nan nan nan 52 38
> ERROR: nan nan nan 52 38
> ERROR: nan nan nan 52 38
> ERROR: nan nan nan 52 38
> ERROR: nan nan nan 52 38
> ERROR: nan nan nan 52 38
>.....
I found that is caused by too long sentence. I have filter out long
sentence, but I received the same errors.
What should I do then to solve this error?

Best Regrads,
-- 
Phạm Thị Ánh Vi
VIEGRID JSC
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support

Reply via email to