>
> What "surface roles" should I identify during parsing? The roles will
> then be used as a start for deeper semantic analysis (i.e. subjects
> tend to become agents, and object 1's become patients).
>
If you're interested in a powerful but non-traditional treatment of
semantic roles, check out my monograph at:
http://www.srv.net/~ram/lexical_semantics.txt
It describes the semantics of an MT interlingua that I've been working
on for the past eight years. I hope it helps!
Regards,
Rick Morneau
[EMAIL PROTECTED]
--
For MT-List info, see http://www.eamt.org/mt-list.html
