[ranch vermin]

Ok, so ive got a memory system, where a state of the sensors is a serial code,  and its completely illiterate, so im having a stab at trying to get to understand something simple autonomously.  But whatever you want to talk about can be completely irrelevant to this, I realize people dont necessarily understand my ideas for sure, simple detached idioms is definitely allowed in this post.

- so when you go about doing language ai,  just remember how anal programming is, and thats how a computer reads things.  which is the complete opposite of language, which is so freeform a computer has no chance at parsing it successfully.


* so these serial codes, are actually language, so it has language, even before its literate at all.

but!!! the words it sees, it cant involve them in its motor. (especially if its just dragging a mouse around in a limited clostrophobic environment, like a web bot does.)
  again-> its hard to associate the word for 'button'  with looking at a button.  same issue.

* its not just looking at shapes,  its actually symbolic of some part of its behaviour somewhere i guess.

* it treats it like pure programming, and then you have a missing links problem, where we automatically fill it with our bullshit, and the computer hasnt got bullshit yet.

* also, it has problems with contradictions, because its just pure programming to it.  (and theres a great many errors in our writings,


so anyone want to add or reject what i said or anything,  just anything language based even GA's,  Ivan had some cool ideas a while back due to some symbolic logic GA, and thats perfectly fine.  anything will do.

[ivan.moony]

I think that natural language is also parseable by computers. Look at "link grammar" for English language, it parses it perfectly, while reporting not only syntax, but grammar errors too.

[ranch vermin]

Thanks Ivan.     I totally agree,  with the points I described.

[Don Patrick]

Language can be parsed "correctly", but that doesn't necessarily lead to the intended interpretation of what's being said. Language is not a single system but a mishmash of loosely defined guidelines and deviations therefrom (slang, idioms, figurative speech). When you program NLP with strict "correct" rules, its interpretation is too limited: People don't speak strictly by textbook rules. On the other hand, if the NLP works with flexible guidelines, its interpretation is not limited enough: it won't distinguish between sense and nonsense. To improve that, I believe you need to apply not just linguistics but also common sense rules and knowledge. That's not one system anymore.

Any of these approaches will get you a certain proficiency towards "correct" interpretation, but I think it is important to realise that you can never get a perfect understanding all the time when using an imperfect language to communicate.

As for linking the word "button" to a visual button, programmers in the past have made enforced learning systems where they point the mouse at a visual button and say "button". Some computer vision AI and/or neural net could discern the button's edges and characteristics to distinguish the element from others. Supposing the program saves the button as an image, next time you say "Press(verb) the button(object)", it could scan the desktop for matching pixels to locate it, move the mouse to those coordinates and click. Interesting idea if I had a use for it.

[squarebear]

The problem I've always had with NLP, and forgive my ignorance here, is that I genuinely don't understand the point of it. Let's say you have the perfect parser that can deal with any sentence. What use is it?

Human: John ate a pizza.
Bot: Ok, I will remember that.
Human: What did John eat?
Bot: No idea but I know there's 2 nouns and a verb in there...

Sure;y, how you deal with input is much more important then breaking it down into its component parts? When someone tells me something, my brain deals with the input as a whole. I don't mentally start breaking it down into noun phrases, verbs and so on.

[Ultron]

NLP and NLU is all fun and coding up until the point you realize that NLU is impossible without intelligence.

To anyone that wants to work with these two systems, keep in mind that as long as they are limited to a chatterbot (single program, single algorithm...) you are only working towards better mimicking of human conversations. Your program can become very convincing - even fool judges and earn you money but it is never going to truly reach us.

Many have already disagreed with this, um... 'Theory', of mine, but take this example...

If you are born blind, do you think any amount of conversations is ever going to give enable you to imagine a color, or understand the concept of colors at all?
It is completely the same to a computer / chatterbot - they lack the senses (or at least the algorithms to process camera/microphone input) and are therefore 'blind' in some ways. How do you think a program (chat bot) is going to understand the word 'apple' if it has never seen, felt or smelled one? 'Apple' would just represent a series of meanless characters to it, much like what 'hydfgerwwf' means to you.

This is in fact how I originally derived the idea that 'understanding' as well as NLU are the ability to connect / associate information from different senses (visual, auditory...) regarding a certain entity (the apple). In our case, when we read the word 'apple' we look it up in our 'database' - we retrieve basic information or specific information required in the current case. This can be size, color (overall look), smell, the sound it makes when hit or bit and even more complex physical properties such as elasticity, bounciness, aerodynamics etc.

I cannot imagine another way to explain the concept of understanding - at least not in a way that would be as logical and make as much sense to me. Also, the point of this post was to get you guys thinking out of the box - get those fancy algorithms and concepts you learn in school out of your head. Throw the Markovnikov chains and classical NLP approaches in the water - derive your own unique idea and combination. These are concepts beyond the average programming problem - but as every other problem, you need to understand the core concept and nature of the problem to your very best, because you are later required to 'teach' a stupid student (computer) how to do it and supply it with extremely detailed instructions. In the case of NLP, it is pretty much figuring out how a great part of your mind works - not a task to be underestimated.

Edit: Squarebear is thinking in the right direction. There is however, a possibility to program a chat bot to understand the sentence as a whole, I suggest exploring Google Translate - the translation changes when you add a new word, but it does more then simply add the meaning of it to the original translation - it (in cases) changes the whole translated sentence.
On another note, we cannot be sure that our mind does not divide the sentence into parts - yes, you do not do this consciously but you don't know what is going on subconsciously.

[8pla.net]

I do not suggest updating this canned response, because I like it the way it is.

The bot said, "No idea but I know there's 2 nouns and a verb in there..."
In terms of Natural Language Processing, shouldn't that be plural,
"there're 2 nouns," (contraction of there are)?

My comment is only intended to map this canned response to mathematics.  I wonder if you realize how interesting your canned response is to analyze?

[ivan.moony]

intelligent bot should be aware of both, of the meaning of the sentence and of its syntax and grammar properties.

[Korrelan]

Hehe...

[Don Patrick]

Human: John ate a pizza.
Human: What did John eat?
Bot: No idea but I know there's 2 nouns and a verb in there...

I've seen you ask this before. Try to see NLP as a pre-processing function: It doesn't have instant direct application. It's like one would say "No idea but I know there's 2 keywords and a wildcard in there..."  . NLP serves to normalise the input, to tell which words are superfluous and which words have key roles in the question. You may not be aware of actively dividing a sentence into parts in your mind, but you are aware of who's doing what in the sentence rather than remembering the whole as a bunch of text. Similarly NLP allows a program to distinguish which subject is doing what action to which objects, and it does so with greater accuracy and disambiguation than pattern matching (not to diss pattern matching, but those are the advantages). But still, it is pre-processing only: After the NLP is done converting English to a more concise format, it's still supposed to send that over to another part of the program that examines it further and produces appropriate output.

[8pla.net]

Well then... Capitalization and contractions
are the differences between
His girlfriend pats a dog & His girlfriend Pat's a dog.






Hehe...

[ranch vermin]

Square Bear,   it is pointless unless you can actually involve what it read in its behaviour.

Where im headed is taking what it read and treating it pretty much like it was ordinary code,  so im trying to make a natural english to machine code conversion.     Then it would be useful, but itll be tricky of course, and simplistic.

Its tricky, even if you wrote the text in direct commandments to it it gets some logic paradigm code for something like this->

sign up to email
 pick a search engine url
 search for an online email service
 access email service
 register
 solve captcha
 access email
 check junkmail
 validate account
goto forum
sign up
solve captcha(x2)
visit email
validate account

for some captcha hunter, and it gets more and more detailed to the point where you cant write anymore to it.  Everything has to be detailed to the end or it doesnt know it,  being a typical computer.

[8pla.net]

Ranch in part said, "im trying to make a natural english to machine code conversion."

I think Squarebear's canned response is great to practice "natural english to machine code conversion" with.  It has mathematics that can be extracted, for example "No" is equal to zero. There is a number 2 and "a" is equal to the number 1. 

It may be unintended, or may just come natural to world champions. However in Squarebears canned response, "there" followed by "in there" which may be mapped to recursion, or a for loop on the numbers 0,1,2,3.  There are some other possibilities for mathematics notation too.   (That's why I like it.)

Ranch, natural language to machine code conversion, I believe, may be a good answer to the age old question of whether or not, a bot knows where it is in the stimulus/response process.

[Ultron]

I see nobody bothered reading my last reply so I will be very short this time...

intelligent bot should be aware of both, of the meaning of the sentence and of its syntax and grammar properties.

No, they shouldn't (or at least, don't have to be). Many people can talk, but they don't necessarily know how to write and break down what they said into grammatical or morphological units. In fact, people have been talking for a long time before grammar was created.


Edit: This may also contribute to me not liking NLP and NLU focusing on strict grammatical rules.

[8pla.net]

Ultron said, "nobody bothered reading my last reply"

Nope.  I did read this entire thread including your replies.

Thanks for writing them, they were a good read. 

Seems all I've been doing lately is reading threads

instead of starting new ones.

I've had a breakthrough in an A.I. project

which I haven't released to the public.   

So, I don't have much to post lately.

However, I am still here most days, reading

and responding to other people's posts.



Oh, and I may not agree with you, but I am willing keep an

open mind about it.  I also respect your opinion.  That is a

good dialog you are opening up on morphology, and so forth.

People may avoid grammar because it slows things down way

too much.  But with a robot, that does not have to be  an issue. 

And secondly, any bot that  can handle grammar is a beautiful

and valuable machine.  And bots, good in grammar are certainly

around by programmers who took the time to train them.