> However, it has not yet been as convincingly disproven as the Cyc-type > approach of feeding a AI commonsense knowledge encoded in a formal > language ;-)
Actually, I would describe the Cyc-type approach as feeding an AI common-sense data which then begs all sorts of questions . . . . ----- Original Message ----- From: "Ben Goertzel" <[EMAIL PROTECTED]> To: <agi@v2.listbox.com> Sent: Wednesday, November 15, 2006 6:50 PM Subject: Re: [agi] One grammar parser URL >> 3. If translating natural language to a structured representation is not >> hard, then do it. People have been working on this for 50 years without >> success. Doing logical inference is the easy part. > > Actually, a more accurate statement would be "Doing individual logical > inference steps is the easy part." > > Appropriately constructing useful long chains of inference steps is an > unsolved problem, just as is mapping NLP into a structured logical > representation. Hence, the fact that nearly all automated > theorem-provers are currently used in "interactive" mode, where the > automated system does a few inference steps and then appeals to a > human for help in search tree pruning (aka choosing what to do next), > and then the automated system does a few more steps, etc. > > If you buy Lakoff and Nunez's theory of the cognitive underpinning of > mathematics (and logic) in everyday embodied physical experience, > then it follows that these two problems (semantic interpretation and > inference control) have a lot of overlap. > > If human logical inference is based on metaphors of embodied > experience, then inference control in humans is largely based on > metaphors of control processes carried out in choosing actions in the > everyday life context. > > In this case, the "common sense knowledge" deficit experienced by AI's > underlies the difficulty that AI's experience with both inference > control and semantic interpretation. > > Our approach in the Novamente project is to give our AI common sense > knowledge via embedding it and interacting with it in the AGISim > simulation world. This approach has yet to be proven, of course. > However, it has not yet been as convincingly disproven as the Cyc-type > approach of feeding a AI commonsense knowledge encoded in a formal > language ;-) > > -- Ben G > > In this case, > > ----- > 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 > ----- 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
