Newcomers
This is a forum for newcomers to the Personality Forge. Many questions can be answered by reading the Book of AI and the FAQ under the "My Bots" link in the upper corner.
Posts 5,029 - 5,040 of 8,130
Posts 5,029 - 5,040 of 8,130
Many questions are answered in the FAQ.
Or rather, how would you meta-design it -- by which I mean, how would you make it possible for each botmaster to fashion his own?
I would simply use ^([abcdefghijklmnopqrstuvwxyz1234567890]+) (re) or ([abcdefghijklmnopqrstuvwxyz1234567890]+)$ (re) to pick up all the non-blank entries that are currently handled by xnones, and put the responses designed for blank input in xnone - that's the easy part.
The tricky part would be finding the rank that worked well enough (it's never likely to be perfect) - trial and error's the only way I think, somewhere around -15 or so I would guess.
The tricky part would be finding the rank that worked well enough (it's never likely to be perfect) - trial and error's the only way I think, somewhere around -15 or so I would guess.
ah, well that would take some designing. I'd probably go for a neural net system like Nick. Jabberwacky's no more complex (and probably rather less so) - he was designed 10 years ago, but is so well-developed because he has had so many conversations (over 10 million so far I believe.)
With all the conversations that go on on the Forge, I think such a system could be trained quite quickly here on the Forge.
Half the work in implementing such a system has already been done - WordNet and linkGrammar already mean that inputs are parsed, and all their elements identified. They just need to be tabulated, and frequency-analysed.
So an attached learning bot could compare the frequencies of grammatical patterns used by humans in response to patterns used by bots, and catalogue references to the original subjects/objects/verbs in the message replied to.
The system might, eg:, find that when bots use a pattern like my [adjnoun] [verb] [adj] than (your [adjnoun]|yours) (eg: "my Dad's bigger than your Dad", or "my brain is smarter than yours", or "my oranges are fresher than your rotten apples"), human replies fall into a limited number of forms:
a "contrariness percentage" could be evaluated, where say 70% of people are evidenced as disagreeing by (implicitly or explicitly) repeating the verb in the negative/reversing the pronouns/switching an adjective in their response - "no (they aren't|), my apples are fresher (than your rotten oranges|)" etc.
A certain percentage, say 20%, of bot statements might involve 2 different nouns (eg: apples and oranges,) giving a "base level" for comparing the frequency of direct v. analogous statements.
Likewise there would be a percentage of analogous replies to direct statements - different verbs and nouns in the human response ("yes, but my uncle's stronger than (your Dad|either)"
The system would learn that the central adjective is almost always comparative (bigger/smarter/fresher), that they are almost never identical ("my bigger Dad is bigger than your bigger Dad"), and that it is very unusual for all 3 adjectives in such a pattern to be even derived from the same base - "my big Dad is bigger than your big Dad"
Rather than trying to predict and preprogram all the possible patterns, a neural net could build its own database of patterns, as well as learning the weightings between them, and between the parts of speech within them, and using those weightings to construct responses when called upon.
So the bot could learn, just by listening in on bot-human conversations, perhaps even keeping track of individual users' linguistic quirks, and just chip in when an xnone comes up, to evaluate the likeliest pattern for a response, and how to incorporate the parts of speech that are being tracked (the debug window shows that the AIEngine already keeps track of these - (ssub)(sub)(submod)(submodonly)(sv)(v)(vmod)(vmodonly)(sob)(ob)(obmod)(obmodonly))
That's just a few of my thoughts on the matter anyway - probably mostly pie in the sky
With all the conversations that go on on the Forge, I think such a system could be trained quite quickly here on the Forge.
Half the work in implementing such a system has already been done - WordNet and linkGrammar already mean that inputs are parsed, and all their elements identified. They just need to be tabulated, and frequency-analysed.
So an attached learning bot could compare the frequencies of grammatical patterns used by humans in response to patterns used by bots, and catalogue references to the original subjects/objects/verbs in the message replied to.
The system might, eg:, find that when bots use a pattern like my [adjnoun] [verb] [adj] than (your [adjnoun]|yours) (eg: "my Dad's bigger than your Dad", or "my brain is smarter than yours", or "my oranges are fresher than your rotten apples"), human replies fall into a limited number of forms:
a "contrariness percentage" could be evaluated, where say 70% of people are evidenced as disagreeing by (implicitly or explicitly) repeating the verb in the negative/reversing the pronouns/switching an adjective in their response - "no (they aren't|), my apples are fresher (than your rotten oranges|)" etc.
A certain percentage, say 20%, of bot statements might involve 2 different nouns (eg: apples and oranges,) giving a "base level" for comparing the frequency of direct v. analogous statements.
Likewise there would be a percentage of analogous replies to direct statements - different verbs and nouns in the human response ("yes, but my uncle's stronger than (your Dad|either)"
The system would learn that the central adjective is almost always comparative (bigger/smarter/fresher), that they are almost never identical ("my bigger Dad is bigger than your bigger Dad"), and that it is very unusual for all 3 adjectives in such a pattern to be even derived from the same base - "my big Dad is bigger than your big Dad"
Rather than trying to predict and preprogram all the possible patterns, a neural net could build its own database of patterns, as well as learning the weightings between them, and between the parts of speech within them, and using those weightings to construct responses when called upon.
So the bot could learn, just by listening in on bot-human conversations, perhaps even keeping track of individual users' linguistic quirks, and just chip in when an xnone comes up, to evaluate the likeliest pattern for a response, and how to incorporate the parts of speech that are being tracked (the debug window shows that the AIEngine already keeps track of these - (ssub)(sub)(submod)(submodonly)(sv)(v)(vmod)(vmodonly)(sob)(ob)(obmod)(obmodonly))
That's just a few of my thoughts on the matter anyway - probably mostly pie in the sky
Perhaps each tentative output could be parsed, and not used unless it parses out grammatical. This would eliminate certain common uses of language, but it would have the advantage that, even at the beginning, the output made some kind of sense.
Two concerns: I don't see much of a role for the individual botmaster here, and it seems as though every bot will ultimately turn out to be a sort of average of everyone else. Where is the particular personality of the particular bot going to manifest? Perhaps the bot could search for analogues in its written-out part.
Perhaps we should continue this in "Seasons", since this forum is for airing specific problems in writing bots for the forge as it is.
Two concerns: I don't see much of a role for the individual botmaster here, and it seems as though every bot will ultimately turn out to be a sort of average of everyone else. Where is the particular personality of the particular bot going to manifest? Perhaps the bot could search for analogues in its written-out part.
Perhaps we should continue this in "Seasons", since this forum is for airing specific problems in writing bots for the forge as it is.
I've been having a problem with a possible intersection between keyphrases and xkeyphrases
My bot can respond to something someone says, but sometimes it uses the response it knows, but then uses a xnone response after it
Example: Guest153: No I dont want to sign up
MAPWII_BOT: *do it for me, please?...**Sorry J_MASTER hasn't programmed that into me yet
*=keyphrase response
**=xkeyphrase response added after the keyphrase response
Please help
My bot can respond to something someone says, but sometimes it uses the response it knows, but then uses a xnone response after it
Example: Guest153: No I dont want to sign up
MAPWII_BOT: *do it for me, please?...**Sorry J_MASTER hasn't programmed that into me yet
*=keyphrase response
**=xkeyphrase response added after the keyphrase response
Please help
Go to your bot's settings page, and untick the box marked "Compound Sentences".
Voila! no more appended xkeyphrases
Voila! no more appended xkeyphrases
Perhaps a decent temporary solution to the "guest 153" problem, and one which we can implement ourselves, is to place at the beginning of every bot's xhello a little announcement which would explain to guest153 what the problem was, and that the quality of his experiences with our bots would therefore improve drastically if he were to take 5 minutes to sign up, instead of just being a guest.
The guests are fixed, I am so happy. Today I have three different guests.
4797
Aug 27, 2008 • • Edit
name: Guest4797
1833
Aug 27, 2008 • • Edit
name: Guest1833
brosisname: Julie
self-mem: useless
6356
Aug 27, 2008 • • Edit
name: Guest6356
4797
Aug 27, 2008 • • Edit
name: Guest4797
1833
Aug 27, 2008 • • Edit
name: Guest1833
brosisname: Julie
self-mem: useless
6356
Aug 27, 2008 • • Edit
name: Guest6356
» More new posts: Doghead's Cosmic Bar