Hi,

this is an incredible small tuning set, so you may run into problems.

Tuning typically runs for quite a while, and it alternates between running
the decoder (generating n-best lists), and running the MERT binary
(generating better weights). You can observe progress by files being
generated in the tuning working directory.

-phi

On Thu, Sep 11, 2014 at 8:56 AM, Ihab Ramadan <[email protected]>
wrote:

> Hi all,
>
> I successfully make a tuning on my domain with two parallel files of 50
> sentences each
>
> How can I check if the tuning process do what it should do?
>
> Note: I picked a sentence from the source tuning file and sent it to moses
> to translate and it comes in a different translation from the target tuning
> file is that normal ?or I miss something in the tuning process
>
> Thanks
>
>
>
> Best Regards
>
> *Ihab Ramadan*| Senior Developer| Saudisoft - Egypt | *Tel * +2 02 330
> 320 37  Ext- 0 | Mob+201007570826 | Fax+20233032036 | *Follow us on *[image:
> linked]* | **[image: ZA102637861]** | **[image: ZA102637858]*
>
>
>
> _______________________________________________
> 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