Hi,

You should proceed with lowercasing both sides of the corpus, then with
building the language model with SRILM and training the phrase model
with train-model.perl.

You can find all the necessary steps on:

http://www.statmt.org/moses_steps.html

hth,
Thomas

On 21/03/11 18:56, AHMED EL-TAHER wrote:
> Hello,
> I recently installed Moses to use in my MSc. research. I want to use
> Europarl v6 de-en corpus with it, so far I tokenised & split-sentences
> for both de &en.
> What next?
>
> Thanks in advance.
>
>
> _______________________________________________
> 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