Re: Dialogue management

> I'm not sure if you're going about it in the best way, but I don't know
> what else to suggest. At some point there has to be a mapping between
> the language model (your concept graphs) and the domain/task model,
> where your slots live. I would recommend using a good declarative representation
> for your ontology and object models, but I'm biased. (I'm working on a new
> Trindikit-inspired toolkit, so I have my own ideas about how dialogue
> managers get built. The jury is still out as far as evaluation goes.)
> 
> However you organize your slots, you should make sure they're compatible
> with the rest of the dialogue management: referent resolution, focus,
> grounding, etc. (Depending on the complexity of your system you might not
> care much about those aspects.)

Hi Carl,
Thanks for the reply. 
When it comes down the real nitty gritty of linking the concept graphs
with a domain model, and to actual interactions with a backend
application, then I couldn't think of or find a better way. This is a
commercial NLP engine, so whatever I choose has to be practical,
robust, flexible, quick to modify, etc.etc .
The scripting language I've developed covers these bases (it also
integrates well with the rest of the dialogue manager, although at the
moment we're just doing limited pronoun resolution, not including
focus or common ground - that's for the next version :), but it takes
time to write and test these scripts.
I was hoping, however, that there might exist some automated, or
semi-automated process for defining such mappings.
I hadn't seen Trindikit until today; I'll definitely check it out.
Cheers again,
Andy