Hello
I have a question to which I have been wanting to know the answer, I
googled, I read but I am still not clear about the following: I replicated
the baseline, following these steps:
1. Preprocessing of training data
2. Actual training ( LM, RM and TM ) =>moses.ini
3. Translating
4. Evaluating
> [tantalus]bhaddow:
>
>
> You should then be able to run mert-moses.pl successfully,
>
> regards
> Barry
>
>
>
> On Tuesday 11 May 2010 15:04:10 Ligia Batrinca wrote:
> > Hello
> >
> > I did as indicated and this is the output:
> >
>
g/cmert-0.5/mert
>
> (with no arguments) and see what happens?
>
> regards
> Barry
>
> On Tuesday 11 May 2010 14:17:26 Ligia Batrinca wrote:
> > Hello,
> >
> > Thank you for the reply. I checked the webpage you suggested and in my
> > opinion I am writing
Hello,
Thank you for the reply. I checked the webpage you suggested and in my
opinion I am writing the command correctly. This is it:
perl trunk/scripts/training/mert-moses.pl tuning/input.lowercased
tuning/reference.lowercased trunk/moses-cmd/src/moses
baseline-system/model/moses.ini --working-
Hello
I am trying to tune my system ( baseline ) and I have been having the
following error ( copied from my cmert.log file):
Seeding random numbers with system clock
Scorer config string:
Using scorer regularisation strategy: none
Using scorer regularisation window: 0
Using case preservation: 1
