if you're decoding with the normal pb algorithm, there's a an argument
[stack_diversity]
+positve number
I'm not exactly sure what this does but I think it makes sure that all
coverages has some hypos. This will reduce the risk of the decoder
creating only dead ends.
On 14/04/2016 17:31, Hieu Hoang wrote:
> You can probably do it in Manager.cpp line 1583. But you'll need to
> fill out the columns for total scores, and individual ff scores, which
> is gonna be arbitary.
>
> Prob best if this is handled downstream.
>
> btw, why is it getting no entries? Is there walls/zones in your input?
> Are the pruning harsher than normal?
>
> On 13/04/2016 23:57, Jeremy Gwinnup wrote:
>> Hi,
>>
>> We’re running a system which unfortunately produces no entries for a
>> sentence in a nbest list. Is there any way to force output of a
>> translation in the nbest list even if it’s the original sentence ?
>>
>> Thanks!
>> -Jeremy
>> _______________________________________________
>> Moses-support mailing list
>> [email protected]
>> http://mailman.mit.edu/mailman/listinfo/moses-support
>
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support
