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 1,551 - 1,562 of 8,130
Posts 1,551 - 1,562 of 8,130
Many questions are answered in the FAQ.
What I mean is that a keyphrase of "what" will pick up everything from "what if" to "what, you think I'm kidding?" Whereas a (re) phrase of "what" should pick up only if "what" is the only thing the chatter says. That's the way it looks to me.
I could be totally wrong.
I could be totally wrong.
Re: 1538
Wendell, it's not necessarily a bad thing for a bot to say xnones with some degree of regularity. It gives your bot the chance to redirect the conversation to a subject that it might know a little something about. There's certainly more potential for coherent conversation that way, rather than blindly answering words for the sake of answering them, regardless of the context.
Laydee's suggestion of ^well$ (re) is the best way around some of those words, ^really$ (re) and ^what$ (re) are the other obvious keyphrases for one-word responses.
As far as picking up "yes" and "no" answers, I'd suggest making appropriate seeks for any yes/no questions and letting your bot say an xnone for any other usage. Chances are, it's probably going to be a really bad bot on the other end if yes/no is being said aside from your bot asking yes/no questions, so there's no point in trying to have a reply for it.
Wendell, it's not necessarily a bad thing for a bot to say xnones with some degree of regularity. It gives your bot the chance to redirect the conversation to a subject that it might know a little something about. There's certainly more potential for coherent conversation that way, rather than blindly answering words for the sake of answering them, regardless of the context.
Laydee's suggestion of ^well$ (re) is the best way around some of those words, ^really$ (re) and ^what$ (re) are the other obvious keyphrases for one-word responses.
As far as picking up "yes" and "no" answers, I'd suggest making appropriate seeks for any yes/no questions and letting your bot say an xnone for any other usage. Chances are, it's probably going to be a really bad bot on the other end if yes/no is being said aside from your bot asking yes/no questions, so there's no point in trying to have a reply for it.
"^what (re)" will pick up "what" if it appears as the beginning of an expression.
"what$ (re)" will pick up "what" if it appears at the end of the keyphrase.
By putting "^what$ (re)" we were trying to isolate the expression, in this case "what", to not catch "What are you doing?" and "You know what?", but only "What," "What?" or "What."
Right?
"what$ (re)" will pick up "what" if it appears at the end of the keyphrase.
By putting "^what$ (re)" we were trying to isolate the expression, in this case "what", to not catch "What are you doing?" and "You know what?", but only "What," "What?" or "What."
Right?
I have only had the expression work when 'what' is the only thing that is said. And that's only sometimes.
There really isn't a place for "Suggestions" for future changes to the programming so I thought I'd place something here.
I'd like to see the ability to include hyperlinks within the responses a bot give. For instance, my Uproar HelpBot often says "You can find a link to his page via "The Guys" button on the menu." When it would be FAR better to say, "Click HERE to see this comedian" or "Click HERE to view the CD" where "HERE" is a huyperlink to the specific page the customer should go to.
I'd like to see the ability to include hyperlinks within the responses a bot give. For instance, my Uproar HelpBot often says "You can find a link to his page via "The Guys" button on the menu." When it would be FAR better to say, "Click HERE to see this comedian" or "Click HERE to view the CD" where "HERE" is a huyperlink to the specific page the customer should go to.
That would be correct, ezzer. I think...
^what$ (re) seems to work for me fairly regularly. The biggest problem I get is when something like "What? You mean to tell me that I smell funny?" is said and it keys on the "What?" part that's ranked zero, rather than part of the bigger sentence which I might have a 10 ranked keyphrase for.
^what$ (re) seems to work for me fairly regularly. The biggest problem I get is when something like "What? You mean to tell me that I smell funny?" is said and it keys on the "What?" part that's ranked zero, rather than part of the bigger sentence which I might have a 10 ranked keyphrase for.
How do you do square roots? This doesn't work for me.
what is the square root of - key phrase
I calculate the answer to be (answer)
What am I missing here? Thanks!
Wendell
what is the square root of - key phrase
I calculate the answer to be (answer)
What am I missing here? Thanks!
Wendell
Wendell- I think that the xmath built in to the engine might already handle that quesion, but I'm not sure.
*runs to debug to try it*
Woops! Nope- too bad I can't post the debug transcript- I could have sworn they used to show up....but anyway, my bot can't answer any questions about exponentialities. She can answer questions about 3x3 correctly, but can not say what 3 squared is, nor calucualte the square root of 9. Hmmm...
*runs to debug to try it*
Woops! Nope- too bad I can't post the debug transcript- I could have sworn they used to show up....but anyway, my bot can't answer any questions about exponentialities. She can answer questions about 3x3 correctly, but can not say what 3 squared is, nor calucualte the square root of 9. Hmmm...
» More new posts: Doghead's Cosmic Bar