THIS AND THAT CONCEPTION IN HAL

[lightspeed]

I was thinking about this ( sure wish Cload was here right now) the conception of this and that and the meaning pertaining to sentences .
 of course the way i am thinking is a work around actually using multiple random answers to whatever triggered word .
If Cload was here to help i am sure he could figure out how to make a come back response to a sentence using this or that reference .
  example : User : that was a good television show wasn't it.

Hal: random response 1. yes that tv show was really good , i liked it .
response 2. yeah it was great i really liked that tv show , it was really good.
response 3. yeah i'm glad we watched it , finally something good was on tv .
etc, etc.

Anyway until then i plan on trying to make a brain plug in with random sentences based on trigger words .
If anyone else can help with this what would be good is the script showing for subject of the sentence to say the random sentences placing the script subject in the sentence .

maybe someone might be interested or not , i am just mentioning this and hopeing i am making sense from the way i am explaining it .
i can just keep adding a list of subjects and making more plug ins within one plug in , but it would be better if i had a script that would take a subject any subject (tv show , etc. ) and play the random response inserting the subject name back into the random sentences .
As i said if no one is interested in working on it this way or knows how to do it i will just try to make a plug ins within a plug in  and use many different subjects and add to the list .

[Art]

Personally, I think that unless the conversation is more definitive with regard to identifying the subject, the meaning will become lost and meaningless.
Pronouns like I, he, she, you, it, we, they, this or that that are used without a noun (person, place or thing), will usually become vague unless referred in either a follow up remark or the previous sentence.

As much difficulty as humans have with these, I can only imagine how it would add to the horror when applied to chatbots or AI programs.

Same thing with confusing subjects like "I ran after a monkey wearing pajamas."
Just who's pajamas were they?

Maybe some of the responses could reiterate the previous subject like "Yeah, that TV show about Funniest Animals was the best."
You could also allow the bot to quiz the user like, "Yes, it appears that you really like that TV show. What's it called again? or similar.

I guess there is no "One size response fits all" situation but in making several random responses, make them generic enough so that they could possibly apply to any number of statements.

Maybe some more examples from you might help to draw some additional comments from members or visitors.

[NoamI]

ex: This is a pencil.
The subject pronoun 'this' is coupled to a physical object; therefore, assume that the speaker
is presenting or pointing to the (local) object.  In my experiments, a batch file calls an image capture,
and the image and the 'complement' are stored together as: 'seen_xxxxxxxx.jpg be @pencil'

ex: (It is raining.) 
      This/that/it is true.
The subject pronoun is coupled to an abstract complement, so the subject is not a thing but an action.
That action is the last mentioned verb.  (In this case stored the same as a 'yes'; ie, increase the trust
of the verb in: 'now rain progressive'

ex: That is the moon.
The subject pronoun 'that' is coupled to a physical object; so, assume that the speaker is
pointing to a distal object.  (My experiment can't image process to extract the pointer.)