[developers] pet ranking with the ERG

Francis Bond bond at ieee.org
Fri Jul 24 19:14:45 CEST 2009


It appears that the pet ranking machinery is behaving wierdly.  When
we parse, as one does, "The dog barks.", the fragment analysis is more
highly ranked, although we think this was not the case in the recent
past.  This happens both interactively with pet, and with the web
demo, using models trained on either jhpstg or wescience.  Using the
current Barcelona release candidate.

Dan and Fran

More information about the developers mailing list