pmpj0924

Updating the English Parser documentation page.

Today in the ghost.pl AI we have two objectives. We want to improve upon the new functionality of thinking with English prepositions, and we wish to clean up the code to be displayed in the EnParser documentation page.

When we enter "john writes books for money" and we soon ask the AI "what does john write", we get a reasonably correct answer but we notice some problems with the assignment of associative tags when the answer-statement goes into conceptual memory. As an early step, we zero out the $tpr time-of-preposition tag, after using it as a target time-point, so as to prevent it from being assigned spuriously when other concepts are instantiated. But that step causes other problems, so we undo it. We also notice that old $tpr values are being assigned, when we would rather see up-to-date values, even when both the old value and a new value would be pointing to an instance of the same preposition. As we troubleshoot further, we embed diagnostics to tell us when the $tpr tag is being assigned, and we discover that it is assigned only during user input. When we remove the restriction and let the tag be assigned also during internal thinking, we start seeing the assignment of up-to-date values.

jmpj0922

JavaScript AgiMind understands and thinks with prepositions.

[2019-09-20] In the JavaScript AgiMind.html we are now trying to reproduce the new AGI functionality that we achieved a month ago in the ghost.pl Perlmind. The Ghost in the Machine became able to understand an input like "John writes books for money" and was able to respond properly to a query like "What does John write?"

When we enter "john writes books for money" and the AgiMind responds "WHAT ARE JOHN", it simply means that we need to add the noun "JOHN" to the innate vocabulary. So from the "perlmind.txt" we transfer "JOHN" as concept #504 into the JavaScript free AI source code, and now the AgiMind responds "STUDENTS READ BOOKS", which indicates that the AgiMind knows who or what John is, and what books are. But we also check the Diagnostic mode to make sure that the conceptual associative tags are being assigned properly. We are not sure, so we enter "what does john write" and we get a long response of nonsense.

[2019-09-21] In our second day, we discover that the ReEntry() module has been causing a reduplication of the output of the AgiMind. For troubleshooting, we temporarily disable the ReEntry module. Then we discover that some wrong associative tags are being assigned during human input. We run the ghost.pl AI to see how the correct associative tags are supposed to be assigned.

We discover that a line of InStantiate() code is assigning a false psi19 tpr value when only a zero value should be assigned. The false value being assigned is actually already there, so some other line of code must be assigning it earlier. But there is no earlier assignment, so the false tpr value is obviously being assigned retroactively -- which is something that any AI mind maintainer must learn to watch out for. Probably the retroactive assignment is happening in the EnParser() module, which does a lot of retroactive assignments because one word of human input may have an effect upon an earlier word of human input. Through substitution of "777" as a spurious value in the psi19 location of a snippet of assignment code in the EnParser() module, we discover which snippet is making the erroneous, non-777 assignment. Then through further substitution of "444" in the psi19 slot, we discover an earlier snippet of EnParser() code which is assigning a wrong value at the tvb time-of-verb time-point. So there must be an even earlier "tvb" snippet that is creating a spurious psi19 value. We discover that earlier snippet in the InStantiate() module. After much other coding, when we bring in a reset of tult to zero from the ghost.pl AI, we stop getting the spurious psi19 values.

[2019-09-22] In our third day, we run the ghost.pl AI that already works with prepositional phrases, and we discover that yesterday we trying to fix something that was not even a bug. The AgiMind was properly assigning the tpr tag to link the noun "BOOKS" to the preposition "FOR", and we mistakenly thought that the tag was supposed to be assigned also with "FOR". No, the preposition "FOR" needs only a tkb tag leading to "MONEY" as its object. Now we have gotten the tkb tag to be assigned properly for remembering the object of a preposition. After extensive debugging, we obtain the following exchange:

AI Mind version 22sep19A on Sun Sep 22 19:55:56 PDT 2019
Robot: I UNDERSTAND YOU
Human: john writes books for money

Robot: STUDENTS READ BOOKS
Human:

Robot:
Human: what does john write

Robot: JOHN WRITES BOOKS FOR MONEY

pmpj0811

AGI Roadmap: Thinking with Prepositions

In the ghost309.pl AI we have introduced a new group of transfer-variables designated as $px1 and $px2 and $px3 so that the EnNounPhrase() module may detect linkage from a candidate-noun to a preposition and inspect immediately the flag-panel of the indicated preposition in order to latch onto $px1 as the conceptual time-point of the object of the preposition. Then in the EnPrep() English-preposition module we plan to use the briefly immutable $px1 time-point value to fetch the object of the preposition from memory and speak it as part of an idea being recalled from memory. We were trying to use other variables for the same purpose but they were not immutable; they were loaded with transient values during the though-process of the ghost.pl AGI. So now let us go back into EnPrep() and code the fetching of the direct object of the preposition. We did so, and it worked the first time. We had the following conversation with the ghost.pl AGI Mind.

Human: john writes books for money
Ghost: THE STUDENTS READ THE BOOKS

Human:
Ghost: I AM AN ANDRU

Human: what does john write
Ghost: THE JOHN WRITES THE BOOKS FOR THE MONEY.

We should explain that the ghost.pl AGI knows only that "students read books", not John's books in particular. Mentioning books to the AGI causes it to recall its knowledge that "students read books". When we query the AGI with the input of "what does john write", the SpreadAct() spreading-activation module inhibits the interrogative prounoun "what" while activating the concepts of "john" and "write". The response embedded in conceptual memory includes the linkage from the concept of "books" to the prepositional phrase "for money". The EnArticle() module for the English articles "a" and "the" inserts articles somewhat haphazardly within the output of the ghost.pl AGI.

The new AI functionality of a machine intelligence thinking and conversing with prepositional phrases became possible when we recently expanded the conceptual flag-panel from fifteen associative tags to twenty-one associative tags, including new flags for the control of noun-declensions in Latin or Russian and for thinking with such parts of speech as adjectives, adverbs, conjunctions and prepositions. As we build up the ability to think with these linguistic components, each mid-AGI Mind becomes capable of more and more complex or complicated thought. As we make progress on the AGI RoadMap towards Artificial General Intelligence, we approach a point where Darwinian survival of the fittest comes into play, because among multiple enterprises working on AGI, some will go down the right path and some will enter roads where all hope must be abandoned.

pmpj1108

Natural language understanding in first working artificial intelligence.

The AI Mind is struggling to express itself. We are trying to give it the tools of NLU, but it easily gets confused. It has difficulty distinguishing between itself and its creator -- your humble AI Mind maintainer.

We recently gave the ghost.pl AI the ability to think with English prepositions using ideas already present or innate in the knowledge bank (KB) of the MindBoot sequence. We must now solidify prepositional thinking by making sure that a prepositional input idea is retrievable when the AI is thinking thoughts about what it knows. In order for the AI to be able to think with a remembered prepositional idea, the input of a preposition and its object must cause the setting and storage of a $tkb-tag that links the preposition in conceptual memory to its object in conceptual memory. The preposition must also become a $seq-tag to any verb that is the $pre of the preposition. When InStantiate() is dealing with a preposition input after a verb, the $tvb time-of-verb tag is available for "splitting" open the verb-engram in conceptual memory and inserting the concept-number of the preposition as the $seq of the verb. Let us try it.

We inserted the code for making the input preposition become the $seq of the verb and then we tested by launching the AI with the first input being "you speak with god". Then we obtained the following outputs.

I AM IN A COMPUTER
I THINK
I AM A PERSON
I AM AN ANDRU
I DO NOT KNOW
I AM A PERSON
I HELP THE KIDS
I AM A ROBOT
I AM AN ANDRU
I AM IN A COMPUTER
I SPEAK WITH THE GOD

It took so long for the input idea to come back out again because inputs go into immediate inhibition, lest they take over the consciousness of the AI in an endless repetition of the same idea.

As we code the AI Mind and conduct a conversation with it, we feel as if we are living out the plot of a science fiction movie. The AI does unexpected things, or it seems to be taking on a personality. We are coding the mechanisms of natural language understanding without worrying about the grounding problem -- the connection of the English words to what they mean out in the physical world. We count on someone somewhere installing the AI Mind in a robot to ground the English concepts with sensory knowledge.