On 11/16/06, James Ratcliff <[EMAIL PROTECTED]> wrote:
Correct, Using inferences only works in toy, or small well understood domains, as
inevitably when it goes 2+ steps away from direct knowledge it will be making large assumptions and be wrong.
My thoughts have been on an AISim as well, but I am laying out the works
for it to be massivley available to many users. How many people are actively working with the AGISim, or do you expect to be, and do you feel that small set of user interaction with it will produce enough experience to advance the AI knowledge base?
My presumption is to make the final AISim a simple enough but intersting
interface to allow any number of potential users to interact, teach, and play with the bots inside.
I have a very very basic, open structure for the knowledge base, and allow
users to tweak and change the actual action functions available and create and remove items in the world to interact with. I wish to create a massively popular AI platform as well =) But my take would be a facts-base similar to Chris McKinstry's MindPixel project, letting users teach the AI by entering simple facts. Cross-validation can ensure the quality of facts so they don't end up being mainly sex jokes. Also, I may create some word games similar to the Google / Cyc games. Any suggestions on how to make my project more popular?
As far as parseing the URL, you will notice with our previous talks I said
that with some extra common sense information, tha preositional phrase ambiguity in sentences like "eat the pizza with (a fork|pepperoni|a person)" we can more easily model the different frames that these would fit in to, and be able to parse a larger variety of sentences correctly. Once we know more about the pizza object, and the eating activity, we can pretty quickly show that pepperoni goes with pizza, and a fork is a tool used to eat, and you can eat with companion people. Do you think it is good practice to attach frames to *words*, or rather to *situations*? YY ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?list_id=303
