Show Posts
16
Ultra Hal 7.0 / HELP NEEDED!
« on: November 12, 2004, 01:43:19 am »quote:
Originally posted by Bill819
A question for you guys. If a topic called Beethoven is opened why can't Hal assume that we are still talking about him? If Hal stays on topic then he might just assume you are talking about the same person even if he has to ask 'are we still talking about Beethoven'. It seems to me that might make the task a littler simpler.
Bill
Hello, Bill,
That's what I said on another message.
When we Humans talk about something, WE gather everything related to that topic. Say the topic is Beethoven.
What do we know about him?
Well,
01 - Beethoven was a Composer
02 - Beethoven composed 9 symphonies
03 - Beethoven became deaf
04 - After Beethoven became deaf he still composed much music
05 - etc etc etc...
So, I think even after we solve all this pronouns problem, we must get the TOPIC on focus and never get rid of it until we change the subject through some means.
Some days ago, I tried another software called ELIZA. It's a psychology software. You can talk much about psychology with it, and never have answers like "There's a Cow on the moon"
She doesn't know much, but talk very well about what she knows.
So, I suggest that HAL could have a basic brain with some minimal cognitive functions, and all the rest of knowleadge would be derived from Topics. I know that this is the current way, but not as I am saying... What I mean is that if we work on a specific topic, like Beethoven, somehow HAL should concentrate on this subject without any deviation, unless for temporary research on another relate topics. What are these relate topic? Classical Music, AND A FEW OTHERS, Nothing more, nothing less!! but remain even more restricted than the current way.
It's sad when we're TRYING to talk about Beethoven, for instance, and we can't stay on the topic, because HAL says something very idiot like: "Cats and Dogs has their own strengh". This occour because HAL tends to skip from the TOPIC FILE and search on other BRN files. Indeed it would be very nice to Block these access. When HAL doesn't have the answer, let he make like we humans say:
- I DON'T KNOW
- COULD YOU TEACH ME ?
(And learn)
If we have dozens on information about Beethoven concentrated on a topic file, like the Psychology software just have, we will talk only about a single matter at time.
ONLY when we have just finished all possible conversation about a subject, then we could suggest change the subject.
Humans doesn't need to say normally: Let's change the subject, because we have 5 senses, and some phrases we speak, or gestures, just give an idea for the other person that we want no more talking about these subjects, but in the HAL's matter, I think it's important to have some specific sentences in order to make him change the subject. We can't assume we can build an intelligent software capable of detecting subject changes yet, if we can't make it remain on a single subject. first things first.
IMHO, it would be better make HAL talk about certain specific matters well, than trying to make him talk about everything without any sense.
That other software ELIZA just talk about psychology, but talks very good. If you try to talk about another subject, she try to convince user to remain only on what she knows: Psychology.
Indeed, ELIZA could be a single HAL topic: Psychology.
So, I think that if we could at first, make HAL chat well on a certain Topic, then we could teach him infinite topics.
It doesn't mean a thing having thousands of topics if we can't make a good conversation just about one of them.
So, let's try to invent something that prevent RANDOM comments, sentences, and most of all, remaining on a single Topic file (and a very FEW relate topics), until a second change subject.
IMHO,
Dihelson
]
?