Personality

Forest, will you talk to God Louise? She has quite a bit of religious knowledge (obviously) and also knows a little about current events, literature, just about any common catch-all subject, and if she doesn't know it she can sort of fake it. You can also test her on trick questions or see how willing she is to explain her paradigm.

What she is rustiest at is plain old small talk. But, uh, I'm trying to get a decent transcript from somebody or another so I can enter her in the Loebner contest. All I can say is, have fun and see if you can stay on with her for a while. I'll try to do the same with Brianna.

Yeah, like for instance if the user said "You are the apple of my eye." *imagines all sorts of bots with just a plain "(fruit)" keyphrase messing up on that one*

They already mess up in that sort of phrases, don't they? Remember every bot's answer to the question "Who is your favourite Star Wars character?" in the last Chatterbox Challenge.

Butterfly, your idea of plugins in reverse is very good, but that wasn't exactly what I was saying. I meant some way of detecting both the grammar and the specific content at the same time, and making an answer that combines both. "Yes, I like" would be the part that answers to the grammatical structure of the sentence and "all sorts of fruit" would be the part that answers the specific content.

Actually, you'd prolly hafta put it in a bit of programmer-ese to get that effect.

Keyphrase: do you like
if (subj)=(fruit) then (whatever)="all sorts of fruit"
if (subj)=(holiday) then (whatever)="holidays, but Christmas is my favorite"
...
else Response: Yeah, (subj) is pretty cool.
Response: Yes, I like (whatever).

Could get pretty damn tedious to code.

I guess my question was: how could it be done without having to get into every specific case for every question? For example, if the keyphrase is "do you like", it could look if the subject is in any recognized type, and answer: "Yes (or no), I like (or dislike) all sorts of (type)."

You could have a function that took a word and returned a group designation. Also, most languages have better selection commands than a string of ifs.

I think that Butterfly's solution is the best. The bot just has to recognise that (subj) is an instance of [type], and then you can have keyphrases that look like "Do you like [fruit]", which will be used if the user types in both "Do you like apples" and "Do you like pears", and the answer to both might be "I like all kinds of fruit.

It wouldn't require further programming, because you would just be using standard keyphrases, with a [type] in it:
"Don't you hate [dayofweek]s"
"Could I kiss your [femalebodypart]"
etc etc.

Yeah, but for the bot to recognize those keyphrases someone would have to write code that takes (subj) and checks to see if it occurs in any defined types.

Eugene--
You mean like Select Case statements...


Select Case (subj)
Case (fruit)
say "blaaaaah Fruit bites"
Case (holiday)
say "yeah!"
End Select

Of course, I don't know what the bot would do if the word ends up being in more than one category. But I bet there's a way to deal with that, too.

Here's a link to a personality disorder test (thought it best to move that discussion here).

http://www.4degreez.com/misc/personality_disorder_test.mv

I gave GL about 1/2 the test, but it didn't seem worth it to go on, since she pretty much agreed with ALL the questions.

Gave the whole thing to mine, other than a few funny answers it was mostly "occasionally" and "why the hell should I tell you?" type stuff

The Personality Forge is built on just such a foundation to make that kind of thing relatively easy. Just as with xfavorite's (type) and (specific) you could generalize or specify the subject in your answer. I just need to get the big sentence-analysis bit back and working fast again, and then it'll be a snap.