On Friday 17 July 2009 16:17:50 Grant Ingersoll wrote:
> Also, do we have any tools for setting up training/test sets for
> Wikipedia examples?  Seems like a generally useful thing to have.
> Take annotated data and automatically split, no?

That certainly would be useful at tuning/ evaluation time: when tuning 
algorithm parameters, selecting one of many different classification 
algorithms or simply trying to find the right feature representation.

I think we need an evaluation module/tool that does training/test splits or 
cross validation and can be used during parameter exploration. At least cross 
validation lends it self well to parallelization, too.

Isabel


-- 
  |\      _,,,---,,_       Web:   <http://www.isabel-drost.de>
  /,`.-'`'    -.  ;-;;,_  
 |,4-  ) )-,_..;\ (  `'-' 
'---''(_/--'  `-'\_) (fL)  IM:  <xmpp://[email protected]>

Attachment: signature.asc
Description: This is a digitally signed message part.

Reply via email to