Hi,

I am not sure what you mean by "VS.2005", but if you check
out the latest version of Moses from github, and use
* kenlm with binaries language model
* binarize the phrase translation table (possibly after filtering)
then loading time should be reduced to fractions of a second.

-phi

On Sun, Aug 26, 2012 at 5:07 AM, saeed farzi <[email protected]> wrote:
> Dear all,
>  I am using Moses (VS.2005) with a large phrase table and a language
> model, but it takes very long time for loading them in to the memory.
> I am looking for a solution to decrease the  loading time. I think , a
> binary version of phrase table and lm may be a solution, but i do not
> know if Moses on VS.2005 can use th binary version of training data?
> also would you plz tell me how i can use KenLM ?
> i run moses with  a binary version of training data in linux. but i
> did do it in windows
>
> tnx in advance,
> --
>            S.Farzi, Ph.D. Student
>     Natural Language Processing Lab,
>   School of Electrical and Computer Eng.,
>                Tehran University
>              Tel: +9821-6111-9719
> _______________________________________________
> 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