What you need to do is store all data in a networked-based,
distributed hash table.  You would then query the phrase table and so
on over the network.

I plan on getting this done for Moses over the summer (for the
language model in the first place).

Miles

On 24 May 2010 18:50, Nata Sekhar <[email protected]> wrote:
> Hello friends,
>
> i am looking for possibites to load the required files needed for decoding
> such as phrase table, reordering table, lm in RAM
> so that i can invoke decoder as when translations are needed for new
> strings.(already have mapped the phrase, reordering tables mapped to disk
> fies)
>
> Simple to say, i need moses engine running all the time and get the strings
> translated as and when needed.
>
> Friends, please share your ideas on this.
>
> Thanks in advance.
>
> _______________________________________________
> Moses-support mailing list
> [email protected]
> http://mailman.mit.edu/mailman/listinfo/moses-support
>
>



-- 
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support

Reply via email to