[Moses-support] Tuning for factored phrase based systems

[Angli Liu]

Hi, what's the major difference between the tuning process for a factored
phrase based system (i.e., surface+pos data) and a simple baseline phrase
based system? Do I need to organize the dev set the same way as the
training set (i.e., surface|pos)? Is there a tutorial on the moses website
on this topic? Thanks!

-Angli
___
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support

[Moses-support] Hardware specs and setup effort

[Martin Wunderlich]

Hi all,

I have already searched the documentation and list archives, but I 
haven't been able to retrieve the desired information that way. I have 
three basic questions:
- What are the recommended and minimum hardware specs for running the MT 
engine?
- How much effort is it to setup the system when starting from scratch?
- And finally, how does it compare to other systems (ModernMT, Phrasal, 
Apertium) in terms of performance? (I know there is variety of factors 
influencing this, but maybe someone has experience with a comparative 
evaluation of these systems or could point me to some good resources)

Thanks a lot.

Cheers,
Martin

___
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support