Sunday, November 10, 2002, 10:54:10 AM, Ben Goertzel wrote: BG> However, including the NLP aspects will make it a LOT harder, because the BG> app would require pretty sophisticated NLP understanding, or it will be BG> incredibly annoying to phrase things in ways the system understands.
Yes, the NLP aspect is tricky. However, in thinking about this I had in mind one of the earliest "impressive" pseudo-NLP systems, SHRDLU: http://hci.stanford.edu/~winograd/shrdlu/ -- I'm sure you're familiar with the demo conversation at the bottom of that page. It involves a lot of trickery, and a lot of nontrivial coding, but it's not by any stretch "full NLP", which I agree should ideally be a "natural" evolution of AGI likely to occur in the near-final stages. The rough analogy with SHRDLU would be that you're communicating about a structured domain in which certain rules apply (paragraphs consist of sentences, sentences consist of words and punctuation, ...) and the concepts are, although more extensive than SHRDLU's, still extremely limited compared to full human-level conversation. In the end you're just manipulating serial text -- you can move, copy, delete, insert, and format it...every operation should break down into combinations of those at root. Of course, something that looks like NLP but isn't quite can end up frustrating users if it responds too often with "I don't understand, please rephrase"...it would take quite a bit of (pseudo-hard-) coding or perhaps, if such a system were 'teachable', a wide beta would do the trick... The only useful non-NLP method of communicating I can picture at the moment is "showing", i.e. defining by example, but this has definite limitations compared to language. Any form of communication sophisticated enough to have the concepts of repetition, exceptions to rules, conditionals, etc. is going to end up as a 'language' of sorts. -- Cliff ------- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/
