"YKY (Yan King Yin)" <[EMAIL PROTECTED]> wrote: On 4/19/07, Benjamin Goertzel 
<[EMAIL PROTECTED]> wrote: 
> I would favor "statistical rule induction", and indeed it might make
 > sense to seed the rule inducer with some hand-crafted rules, to guide
> its learning in the right direction.

 Sorry, I made a mistake -- I forget things that I have previously thought 
through!  "Rule-based" is not exactly my idea.
  
 Actually my ideal system is one that uses induction, abduction, and truth 
maintenance.  It allows the AGI to start as a tabula rasa  baby, and then learn 
language incrementally.  So, web-surfing lay people can teach it.  The only 
problem is that the algorithms involved are very complex...
  
 It's misleading to call my approach rule-based, because that reminds people of 
old-time expert systems.  It can be more aptly termed "a consistency-seeking, 
learning system built on a logic-based KR". 
  
 If you're interested in this approach we may have some collaboration.  I am 
currently looking into algorithms for logic-based abduction.
  
> I really doubt that a collaboration of web-surfing NL enthusiasts are
> gonna create better rules than the linguistics community has done so
> far.
 
 You're right.  It is unreasonable to expect web-surfing lay people to be able 
to enter rules directly.  It is only reasonable to expect lay people to talk 
with and teach a baby AGI, in NL. 
  
 Consider this reasoning:
 1. The NL task is ultimately to map NL sentences to the KR scheme.
 2. For statistical learning, a labelled corpus is much more preferable to 
unlabelled ones.  In other words, you'd want a corpus with NL sentences 
translated into KR statements, side-by-side. 
 3. Lay people cannot master a real KR scheme (eg Cyc) because it's too 
complex.  Therefore, they cannot produce *labelled* training examples.
 4. A well-funded project may be able to translate a large number of NL 
sentences to KR, similar to the Penn Tree Bank for syntax, but that takes $$$.
  
 It seems that the best bet is to let the AGI learn language like a baby.
 
> Why not just create a Web UI allowing users to enter additional rules
> for some existing grammar, such as the Link Grammar (my personal fave)
> or XTag (too complex for my taste)?  I really think few people will 
> gain the needed skill and understanding to contribute.  But we did add
> some rules to the Link Grammar for a paid NLP consulting project a few
> years back.
 
 That was my first-blush approach, but still impractical.  Very few people can 
master a KR scheme as well as the computational grammar rules.
 
> Basic English is not all that unambiguous.  Sentences may be short but
> anaphora and prepositions remain.
> 
> If you're going to restrict your AI to a special subset of English,
> then it can't read free text anyway... all you can do is chat with it. 
> So why not just chat to it in Lojban which has full expressive power,
> barely ambiguous semantics, and totally unambiguous syntax?
 
 Lojban has it strengthes, sure.  But the problem with Lojban is that so few 
people can speak it.  We need a big community of "AGI babysitters". =)
  
 YKY

Well some form of Basic English shoudl be the best approach, because we need 
something halfway between the two, English and the direct KR, english is too 
complex, and Lojban and Cyc are too specific to easily speak in and require the 
regular user to use.  
  So if you were able to parse basic english to a reasonable effort you should 
be able to have a system that showed a regualr english story and a basic 
english one side by side, and let the users convert between them to help the AI 
understand and learn the things it doesnt know.
  While a simpler english form may still have some ambiguity, much of it is 
reduced just by the shortness and simpleness of the format, no complex compound 
sentences gives a very big boost. 
  Anyone has the ability to "reword" an english sentence into a simpler format 
though, without a lot of trouble.
  I worked a bit on a small parser that just sought to break up the complex 
sentences, and a good deal of information is given after you have a much 
simpler format.

>From a news article:
 Both Brown and Gatewood  were asleep when the officer pulled Harris over.
AI: Complex sentence, help me rephrase this.
The officer pulled Harris over.
 Both Brown and Gatewood  were asleep. 
 AI:  OK, translating -  pulled_over(officer, Harris)
were_asleep(Brown & Gatewood)

So patterns can be learned with the help of some users, without them knowing 
any KR techniques, and when it gets down to simple statements it is much easier 
to know these statistically.

James Ratcliff


_______________________________________
James Ratcliff - http://falazar.com
Looking for something...
       
---------------------------------
Ahhh...imagining that irresistible "new car" smell?
 Check outnew cars at Yahoo! Autos.

-----
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

Reply via email to