Co-occurrence was really the wrong word. I forget it has the bag-of-words 
connotation. I imagine an efficient lookup could be designed by using a hash 
table with hash values based on a bag-of-words approach, but actual recognition 
would have to be based on the structure of the sentence, as you say.

Anaphora resolution is designed into the system. The system doesn't pick a 
single object that can be matched by a pronoun. It picks a list of them based 
on recency of use, and links the pronoun to each of them via links with 
strength based on recency. It then performs higher-level analysis based on the 
object attributes indicated by the pronoun and the context in which the pronoun 
is used. Reasoning, which is as yet unimplemented, will be able to step in and 
further modify these link strengths based on additional information garnered 
from inference.

This approach does produce some combinatorics, but with a reasonable upper 
bound dictated by the size of the recency list, which can be set to something 
comparable to the limits of human pronomial references and still be well within 
the computational constraints of the system.

Interesting that you mention higher-level structure to the conversation being 
important to understanding. I recently read an article about a research team 
building a system that does exactly that, using a template-based approach. I am 
probably wildly wrong, but I *think* it was a fellow named Wilson and the 
system was named GENESYS. I'll look it back up and get you something definite 
here in a bit.

I do think that reasoning and learning should always be running in parallel to 
the behavioral and perceptual processes, and should be able to step in and make 
adjustments when appropriate. That's the reason for going with a universal 
format for all information processed by the system, namely semantic nets.


-- Sent from my Palm Pre
On Oct 18, 2012 5:20 AM, Jim Bromer <[email protected]> wrote: 

I think an idiom has to be recognized as a phrase.  Using co-occurrence is 
an interesting idea.  However, this is on the edge of the area where I 
feel a little uncomfortable with the over-reliance on a conventional 
superficial method like co-occurrence.
 Someone mentioned anaphora recently.  While your semantic parser 
might pick out some variable-like words (especially superficial variables like 
"he" or "it") it is going to miss a phrase which refers to someone or something 
that had been mentioned or will be mentioned in a subsequent remark.  
While it is easy to figure a scheme to deal with this, the problem is 
that it could lead to a substantial increase in combinatorial complexity.  
For example, even if you looked at possible relationships to and 
from a noun-phrase to other noun-phrases you might still miss the relationships 
that form a broader subject. (For example, a number of 
sentences might be used to build a structure of a subject being 
discussed by using a diverse set of examples, and your relational 
searches might miss this or lead to misleading conclusions).
 One simple explanation (but not necessarily a solution to the programming 
problems) is that intelligence is always an active process 
of learning.  So even when your mind is not working hard it is always 
figuring out relations.  In one sense contemporary AGI programs are 
designed this way but in another sense they are not insightfully designed this 
way.  So (for example) while the underlying programming that searches 
for possible relations might be actively searching for these relations, the 
nature of these searches may not be foremost in the programmer's mind as 
he writes his code.  So the search might be constrained or broadened 
by the kinds of concepts that it is considering, but the search process itself 
is not being looked at by the programmer, or it is only being looked at in a 
superficial conventional way. I am saying that it might be possible to create 
something a little novel for the search process itself as well as rely on the 
more conventional kinds of searches which is essentially designed around a 
function that accepts a group of parameters.
 Jim Bromer

On Wed, Oct 17, 2012 at 10:00 PM, Aaron Hosford <[email protected]> 
wrote:

I agree fully with regards to handling multiple possible meanings to a 
sentence. My parser doesn't stop with a single interpretation. It builds a long 
list of possible interpretations, along with scores based on the parser's 
estimation of the likelihood of the interpretation. The client code then 
iterates over the list of interpretations in order of score, rejecting 
interpretations that aren't meaningful or don't fit the context. The parser 
modifies its scoring according to which interpretation was accepted. So it's 
possible to handle puns and other double entendres by accepting more than one 
meaning.


The client, which converts the parse tree into a semantic net, doesn't restrict 
itself to a single interpretation of a given parse tree, either. Links are 
given "soft" truth values, with frequency and certainty values inspired by Pei 
Wang's NARS system. This means that the same network can simultaneously 
represent multiple, competing interpretations through lowered certainty levels. 
As new information becomes available, the system updates the links' truth 
values and certainty levels until a clear winner emerges. I think this ability 
to revise interpretation based on contextual information received both before 
and after the sentence is parsed, as well as to weigh competing or 
contradictory information, is key to the sort of flexible thinking human beings 
exhibit.


One thing which I have not yet implemented and am still undecided on is the 
handling of idioms. I suspect this will end up being some sort of lookup based 
on word or concept co-occurrence, i.e. a connected subnet of the network 
representing the sentence will be encoded and used as a key into a table of 
idioms. Identifying the idiom rapidly through this or another approach is the 
hard part. Once an idiom is recognized, it's simply a matter of applying a 
graph rewrite to generate an alternate meaning for the sentence, and using 
links with soft truth values to identify the new, competing interpretation. The 
system can then resolve between the competing interpretations using the same 
mechanisms it would for more subtly different interpretations. I think many 
idioms originate as crystallized, highly re-usable analogies. Maybe that can 
provide some additional insight into the design when the time comes.



On Wed, Oct 17, 2012 at 5:20 PM, Jim Bromer <[email protected]> wrote:


Aaron Hosford wrote:
I get the impression that you're saying (both here & in your previous 
emails on Algorithmic Synthesis) that claiming two things are associated isn't 
enough -- that the *kind* of association is important too.


 -Yes I do feel that way although I probably wasn't thinking of that when 
I wrote my message.  An association may belong to many categories of a 
*kind*.  This is important because we can usually abstract or generalize 
from an 'idea' or 'ideas' in many different ways and these different 'kinds' 
of abstractions are things that can become concepts of their own 
(referring to the nature of the abstraction).



Aaron Hosford wrote:Roger Schank has provided quite a bit of inspiration to me, 
based on how he represents meaning as semantic links connecting basic concepts 
together. From the natural language perspective, it is relatively easy to see 
how this can be implemented. I'm not alone in having successfully built a 
parser that extracts a semantic network from a sentence which represents that 
sentence's meaning with a fair degree of accuracy.


 -I really liked Schank's work as well.  I think that 
old world semantic networks simplified the potential for meaning too 
much. So while you might get closer to a single constrained meaning of a 
sentence, you would also lose many of the undertones, highlights and 
colors of the sentence that can help to make the sentence 
meaningful.  So here it is again, it is not enough to take the shallow 
level of meaning that might be derived from a tightly 
constraining analysis of the superficial sentence.  You have to 
be looking for other kinds of meanings to see if the words of the 
sentence (or 'ideas' of the sentences) can be better interpreted in other 
ways. 


 I will have more to say about this. Jim 
Bromer      
  On Tue, Oct 16, 2012 at 3:34 PM, Aaron Hosford 
<[email protected]> wrote:

Well, I'm not really clear what you're getting at, mainly because when talking 
about intelligence & thinking, all the terms we have to  use are so 
versatile & loosely defined that to narrow down what's being communicated 
to a sufficiently narrow set of interpretations, we have to say so much that 
the key point becomes a needle in a haystack of contextual information. I'm 
sure what you're saying here makes perfect sense to you, but the words you're 
using aren't sufficiently grounded (or are grounded differently for you than 
for me) that I don't follow.




I get the impression that you're saying (both here & in your previous 
emails on Algorithmic Synthesis) that claiming two things are associated isn't 
enough -- that the *kind* of association is important too. I agree with you 
here. It's not enough to say, these are the parts and they go together; how 
things connect must be considered to have productive thoughts about them. This 
is directly analogous to the treatment of sentences as bags of words: It's not 
enough to just look at the set of words to determine the sentence's meaning; 
the way they connect to each other matters. This is where I'm starting from in 
my system's design.




#1: Figure out how the human mind represents meaning.#2: Figure out how to work 
with meaning to produce intelligent thought.
#2 cannot proceed until #1 is effectively implemented. Roger Schank has 
provided quite a bit of inspiration to me, based on how he represents meaning 
as semantic links connecting basic concepts together. From the natural language 
perspective, it is relatively easy to see how this can be implemented. I'm not 
alone in having successfully built a parser that extracts a semantic network 
from a sentence which represents that sentence's meaning with a fair degree of 
accuracy.




>From the perceptual perspective, it is also fairly easy to see how semantic 
>networks can be used to represent information. The visual field can be 
>broken into chunks or fields, each representing an object or a part of an 
>object. The objects are semantically connected to each other according to the 
>spatial or behavioral interactions they are participating in, and the parts of 
>objects are semantically linked to the objects and other parts according to 
>their arrangement. Nodes representing objects and parts generated at a 
>particular time can then be interconnected across multiple time frames, 
>resulting in a narrative description of the field of vision as a sequence of 
>events unfolds. Other senses can be integrated directly with vision in the 
>same manner.




Higher levels of abstraction can be generated by looking at patterns in objects 
(just as objects are generated by looking at patterns of parts) and adding 
additional nodes which serve to group together the lower level nodes into 
patterns based on link types. Memory stores only these higher-level nodes 
(parts, objects, & upward), not the lower levels which served in their 
construction, and memory fades from the lowest levels upward, causing us to 
lose detail but not gist.




Language (or rather the semantic nets which represent meaning) can then be 
treated as predicates which match the upper levels of the perceptual network, 
acquiring a non-Boolean or fuzzy truth value based on how well they match 
perceptual information retrieved from memory. Thinking is implemented at this 
level, as well. Thinking processes serve to generate truthful predicates based 
both on direct observation of higher-level perceptual subnets, and indirect 
reasoning based on observed patterns in these perceptual subnets. Reasoning can 
reach as far down the hierarchy of nodes as was stored in memory, but starts 
from the top-most level and does not reach down to these lower levels except 
when higher-level abstractions indicate that additional or finer-grained detail 
is needed. (This is how we avoid the combinatorial bottleneck.) Predicates 
generated by observation or reasoning can be directly read off and converted to 
natural language using the same mechanisms as the semantic parser, but in 
reverse. (I've got much of this mechanism working, too.)




I have yet to start work on the perceptual systems, but the semantic 
representation of meanings/predicates is rolling along nicely. Perception is 
going to take a lot more work, because there's a lot more data to process, but 
I'm watching the research as it unfolds, and I see a lot being done in the 
direction of object detection. Even if we create a perceptual system that isn't 
as detailed in representation as human perception (i.e. it represents objects 
and their interactions, but not their parts or lower level abstractions), it 
should be possible to start work on a reasoning system that handles 
higher-level abstractions and is able to communicate its thoughts verbally or 
in text. This is the key point at which artificial general intelligence gains 
traction as a technology worthy of financial investment.





On Sat, Oct 13, 2012 at 9:21 PM, Jim Bromer <[email protected]> wrote:




Well I just remembered why people have been so distracted by the analysis of 
superficial data.  Because it is easy.  Because it is easy for an 
automated program to analyze the superficial features of the input media and 
how the data environment of the medium is affected by the program's output but 
it is hard to figure out how the program would analyze hidden meaning.  
But, most of the people in this group talk as if their ideas would 
be powerful enough to discover underlying meaning or underlying relations 
in the data environment.  So then what started as a first response to a 
problem description simply became the dogma.  (Yes that is 
really what happened.  Does anyone disagree? (No?!.)) 




  So while the rehashing of the first step may 
have seemed like it was an important primitive to 
explain to the inexperts, as it became the reigning focus of all such 
conventions of presentation it became the dogma of the genre.  Because 
people somehow found a rationalization to avoid taking the next step (to 
explain how deeper relations between ideas, concepts or operations in the IO 
data environment could be integrated and discerned) it became a blocking 
dogma.  In order to join the club, so to speak, you had to start by 
avoiding the next question.  




 You often feel that you have already thought about an idea because 
you have examined a high-level concept which might be a categorizing principle 
of the idea.  For instance I was interested in 'associations' so when I 
encountered the word 'correlation' I simply felt that I had already considered 
the concept as a kind of association.  A correlation can be considered as 
a type of association so it seemed like I had already had handled that 
relation.  However, it just is not the same thing.  A correlation may 
be a kind of association but it is bound with another association as well, the 
concepts that defines the nature of the correlation.  So a correlation is 
not -just- an association.




 You have to take it to the next level and it has to start in your 
mind. Jim Bromer 

 



On Sat, Oct 13, 2012 at 8:39 PM, Jim Bromer <[email protected]> wrote:

I think that misunderstandings can occur when one person presents an idea 
which possesses some features which resemble features 
of another idea that a listener has already considered. If the resemblance 
is somewhat superficial, especially if the superficial resemblances lie at a 
shallow underlying level, a person who is listening to the idea 
may feel certain that he was totally familiar with the idea even 
though he might not really get what the speaker was saying. The 
listener may casually miscategorize the presented idea by 
thinking that it was the same as the similar idea he had already 
considered. Good ideas are often unoriginal or unsurprising and this vague 
familiarity can strangely have a non-intuitive effect to further a 
misunderstanding.  The reason that this can occur is that ideas sometimes 
need to be emphasized or 'formalized' in some way in order for them to be fully 
appreciated.  






 I for one would like to be able to understand why people who should be 
interested in something I have said aren't. The answer to this question 
has always been somewhat elusive.  A primary characteristic that 
can produce this kind of misunderstanding is superficiality in the 
listener.  (Of course the new idea may be poorly presented and we all make 
a variety of mistakes, but I am often confronted with the experience where I 
have repeatedly presented a commonsense idea and I can't find anyone 
who acts like they understand what I am talking about).






 But is there anyway you can verify (at least for yourself) 
that someone who should be reacting intelligently to what you are saying 
is actually reacting at a too-superficial level?  I have found that 
there is a way in this group because we are constantly talking about 
artificial means of creating "personality" traits.  
If someone repeatedly emphasizes superficiality of association as a 
presumption for the basis of intelligence then there is a chance that he 
might unitentionally be describing a method that commonly 
underlies his own thought processes.   






 For example, I have described a process of synthesis where a new idea is 
formed from the association of two pre-existing ideas based on a reason.  
The reasons can be superficial, like a superficial co-occurrence (of time 
or position) or a superficial similarity, but then I also emphasized that 
ideas may be related by complimentary conceptual roles.  Furthermore, 
I have emphasized the importance of conceptual structure which is a term I use 
to stress that there may be a greater complexity to putting ideas together than 
just relying on one superficial feature.






 So now, if after expressing this and pointing out that the purpose of 
combining ideas is to create some semantic or operational structure, I see 
someone restating the insight that co-occurrence and similarity are 
the basis of correlation and association I will have some substantial evidence 
that my ideas were not appreciated by that person because he tends to 
be over reliant on superficial methods of thought.  
Co-occurrence, similarity, simple association and analogy are all examples of 
relations between ideas that are typically shallow. The superficiality may not 
be at the surface level, but it is usually not going to be that deep.  The 
declaration of these relations are all ok but I feel that if the presenter is 
going to explain how intelligence works then he needs to take it to a deeper 
level.






 Of course, misunderstanding can also occur when a phrase is taken to 
refer to a superficial aspect of thought even though the speaker 
intended it to refer to deeper relations as well.  But I think the 
declaration that the basis of correlation is co occurrence, similarity and 
associativity has just been too over-used to still be 
considered sufficient as a presentation of the basis of thinking. 
Thinking gets a little deeper than that.






 Jim Bromer





  
    
      
      AGI | Archives

 | Modify
 Your Subscription


      
    
  







  
    
      
      AGI | Archives

 | Modify
 Your Subscription


      
    
  







  
    
      
      AGI | Archives

 | Modify
 Your Subscription


      
    
  







  
    
      
      AGI | Archives

 | Modify
 Your Subscription


      
    
  







  
    
      
      AGI | Archives

 | Modify
 Your Subscription


      
    
  






-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-c97d2393
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-2484a968
Powered by Listbox: http://www.listbox.com

Reply via email to