oops .. . change the above…..  in AI literature they don’t speak of “bots” . . . but “intelligent agents”, so correction there.  (again . .edit button Erwin!)

Victor Shulist - Mar 15, 2011:

In your system, I believe you later want your code to be put inside a physical robot perhaps?

That is indeed my goal.

For your project you are indeed completely free how you define those ‘parts of reality’, but I’m sure that if you go that route it will certainly be beneficial for the quality of your results.

‘that route’ meaning the whole idea of the “Out of Band”  + / - feedback?

This:

Victor Shulist - Mar 15, 2011:

I think what I will do is:

a) the bot itself
      this is right now clues.cpp , the main core engine that parses, and figures out how to evaluate each parse tree, trying to pick one with the most semantic relevance.

b) its enviornment - well, this could be the current state of the dialog with the user, it could also be all the parse trees that it has to work with, also its knowledge base, and its previous talks it had with the user.  maybe even its connection to 3rd party database, the interent, facebook, wikipedia, whatever.

c) the goal of the bot ... to figure out what the user is asking for, or what they are commenting on, basically what they are talking about, and figure out what combination of ‘resources’ to use in order to work out a plan , execute that plan, and give response to user.

Ahhh yes, this is the hole idea of a HOLISTIC solution.  The state of the conversation, and figuring first what the bot should do, then figure out how to do it, then do it.  Then get feedback.  That is the OVERALL theory of operation.  Then you drill down deeper and deeper into the details.

Above. . . .

      “The state of the conversation . .. . . . . .”

to . . .

      “Based on the state of the conversation… . . .”

Of course, for now, I’m in “Test SQA” mode.  Which means entering Facts, and asking questions - this is to test its ability to understand statements, which may be stated in almost infinite number of ways, and still extract the essential information.

Once that is accomplished and it has learned everything about grammar . . .AND a lot about semantics and knowledge of the world, on we go to those higher levels of functionality.

It sure is a long road. . .but I’m getting there!

SQA test mode, by the way, SQA =  statement,  question, answer.

Hmm the “other’ category seems to be well in front?

My understanding is based on study of ‘communication theory’, that language is simply a tool for transferring data, and information.

Knowledge is formed by the recipient utilizing their own experience, contextual settings - by processing information received, the use of language as communication does not in itself transfer knowledge.

A simple example of this is explaining to a person what being burnt feels like - words alone can transmit information, but until a person experiences being burnt , they are not truly knowledgeable.

Knowledge is formed by the recipient utilizing their own experience, contextual settings - by processing information received, the use of language as communication does not in itself transfer knowledge.

A simple example of this is explaining to a person what being burnt feels like - words alone can transmit information, but until a person experiences being burnt , they are not truly knowledgeable.

I’d have to agree with that, we tend to need some ‘previous experience’ to properly place things.

Michael Stoddart - Mar 20, 2011:

Knowledge is formed by the recipient utilizing their own experience, contextual settings - by processing information received, the use of language as communication does not in itself transfer knowledge.

This is exactly the point I’m defending here on the forum for a while now

Small addition….

From the previous point made by Michael, it should be clear that you can not use previous ‘exchange of language’ as a base for that ‘experience’. This is of course the exact point of the ‘symbol grounding problem’.

Michael Stoddart - Mar 20, 2011:

My understanding is based on study of ‘communication theory’, that language is simply a tool for transferring data, and information.

Knowledge is formed by the recipient utilizing their own experience, contextual settings - by processing information received, the use of language as communication does not in itself transfer knowledge.

A simple example of this is explaining to a person what being burnt feels like - words alone can transmit information, but until a person experiences being burnt , they are not truly knowledgeable.

These are great working definitions of information vs knowledge. Unfortunately, a lot of energy gets wasted in semantics debates when these two ideas get muddled.

Dave said:
There almost has to be some sort of internal self-evaluation function or routine that continually reviews “known” data (e.g. memories, “values” or morals, etc.) in the background, that acts as a sort of “subconscious” component.

Finally someone wanders into more of reality. I would guess that more than 90% of thinking and knowledge is in the subconscience never to be accessed by language. It is the illusion to believe that constantly running dialog in your head is what makes your mind.

C R once said we can only think of a very few things at a time. Not true. Otherwise we couldn’t remember anything but a few moments.  Yet memories flow in and out of our awareness like magic.

And there is the point of it all; what we are conscience of and what we don’t have any idea of what is going on inside our brains. That internal conversation which spills out into the physical is you continually practicing how to express yourself.  It is an instrument of personality.  With a persona you can communicate.

I wonder what was going on in Helen Keller’s mind.  She never heard the words in order to have that little voice working so hard to explain the world. Her definition is “Knowledge is love and light and vision.” On language she states “Once I knew only darkness and stillness… my life was without past or future… but a little word from the fingers of another fell into my hand that clutched at emptiness, and my heart leaped to the rapture of living.” And another quote, “People do not like to think. If one thinks, one must reach conclusions. Conclusions are not always pleasant.”

Wow!!

I forgot why I liked chatbot postings.  Great discussion!  Nothing here any of my family or friends locally would ever appreciate or find remotely interesting. =)

When I began reading this post, I thought of a theater in which a play was about to start. There were actors, props, and some initial situation filled with implied stress (e.g. a room full of people with someone dead on the floor when the lights come on).  Additionally, I consdered thta there was no script because this would be ‘ad libed’ (sp).

One more thing before the play begins. There is no written or spoken speech during the performance.  Actors would communicate via body language, gestures, prop manipulation.

So knowledge would be present.  Actors would share some common knowledge such as who is in the room and perhaps what they observe. There would be differences of interpretation because people think differently.

A significant amount of actor energy would go into ‘communicating’ and moving the play along.

That’s as far along as I got in this mental exercise.  So I checked ‘other’ in the poll.

Regards,
Chuck