Re: [lkb] generation ranking in LKB

G'day,

On 10 July 2010 18:00, Stephan Oepen <[email protected]> wrote:
> any number will activate n-best selective unpacking, so you can choose how
> many realizations you want returned (at most).  as for the specific model,
> it's the ‘combined’ model from the EMNLP paper; however, just now i'm not
> sure the MEM file has been updated for the change in ERG rule identifiers.
>  in principle, that model should be retrained, i guess.  we have been a
> little slack about this in recent ERG releases ...

Is this also turned on during interactive parsing/generation, or only
for batches.   Is there a way to turn it on for interactive use (e.g.
when parsing/rephrasing/generating)?


-- 
Francis Bond <http://www3.ntu.edu.sg/home/fcbond/>
Division of Linguistics and Multilingual Studies
Nanyang Technological University