Hi,

you could just handle this in pre- and post-processing.

-phi

On Tue, Jul 6, 2010 at 2:12 PM, Raphael Payen <[email protected]> wrote:
>> * when decoding you first replace the number with the NUMBER token, and then
>>  replace its translation NUMBER token with the number in mind.
>
> For this replacement, I need to keep the value of the number number
> along the translation, so the best option seems to add it as a factor
> ? Then, all other words of the corpus need to have an empty factor.
> It's not such an awful problem, but it seems strange.
>
> _______________________________________________
> 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

Reply via email to