[developers] coreference problem fixed
Emily M. Bender
ebender at u.washington.edu
Fri Aug 15 20:12:52 CEST 2008
I think this is different from other kinds of spurious ambiguity, in that
from a morphosyntactic point of view, the derivations look identical
(the discriminants code can't distinguish them, for example).
Since I haven't been able to figure out how to rework my subrules to
avoid this problem, if you have the time to look into it, I would
appreciate it :)
On Fri, Aug 15, 2008 at 11:08 AM, Ann Copestake
<Ann.Copestake at cl.cam.ac.uk> wrote:
> thanks - I haven't thought about the morphology much recently - it's easy
> enough to stop that in the code, and I can see why you'd want that behaviour,
> but I'd have to think a bit about what the formal issues might be.
> We don't eliminate spurious ambiguity in general.
More information about the developers