Four thoughts . . . . . 1. I look at the restricted vocabulary as what grounds the AGI. If the "restricted grammar kernel" is complete (a *HUGE* task), the AGI is effectively "embodied" in that kernel.
2. The kernel (or seed) is simply the starting point. As you say, you shouldn't restrict communication/interaction with humans to the set of words . . . BUT . . . in order to be truly communicating, the system must ground any conversation by being able to (internally) relate all terms back to the kernel. 3. Concepts are trees or nets (i.e. that can get quite large). In order to really effectively communicate with a concept, it really needs to be labeled. Doing this with real English words will make it a lot easier for your AGI to communicate. 4. Your AGI will be most efficient/effective if you compress knowledge as much as possible. The first place to do this is in the knowledge-base where you store your concepts. This can get tricky and cause problems unless *you/your design* clearly distinguish between knowledge and data (i.e. if pigeon is a bird and bird flies then pigeon flies should not be in the conceptual part of your database -- though examples where you are told or see this fact does need to be in the supporting facts part of your database). Penguin goes into the concept-base as a bird that doesn't fly in the same way in which other exceptions allow open-ended reasoning) ----- Original Message ----- From: Jean-Paul Van Belle To: [email protected] Sent: Monday, April 30, 2007 3:35 AM Subject: Re: [agi] HOW ADAPTIVE ARE YOU [NOVAMENTE] BEN? Not quite on the grammar topic but on the related topic of 'restricted vocabulary': A couple of us have been/are considering using Simple (or the alternative Basic) English or other restricted vocabulary sets. IMHO There are actually two issues here: (1) you may wish to have a simplified (i.e. reduced) representation of the knowledge base i.e. using a minimal set of concepts/attributes/etc. as a starting point (for those of us who don't bootstrap *all* knowledge :) - in this case it is fine IMHO - the system can learn the new concepts later. (2) you may wish to restrict communication/interaction of humans with the system to the set of words. This is *NOT* a good idea: most words outside the simple/basic vocabulary set actually respond to refined concepts (usually as per definition of the word) and you will have to have - somewhere in your system, depending on your knowledge representation scheme - a pointer (or whatever) to the data item that representscorresponds to that (complex or composite) 'concept' ANYWAY. But then it is silly not to use the real english word as the token/label for that node in your database. BTW my two arguments for this are (2a) this is exactly the reason why kids can pick up new words at the rate of 10+/day ... they hear the word and it maps directly onto a construct/concept that is already present in their mind, they don't have to construct an entire new structure in their mind; (2b) when you look at these lists of proposed new (rather silly) words (a la "the meaning of liff" etc.) we *all* recognise the concepts/feelings/situations which these words map to and can see quite well why these should/could be given a special word. Jean-Paul Van Belle On 4/29/07, Richard Loosemore <[EMAIL PROTECTED]> wrote: > The idea that human beings should constrain themselves to a simplified, > artificial kind of speech in order to make life easier for an AI, is one > of those Big Excuses that AI developers have made, over the years, to > cover up the fact that they don't really know how to build a true AI. > > It is a temptation to be resisted. ------------------------------------------------------------------------------ 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/?&; ----- 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/?member_id=231415&user_secret=fabd7936
