The AI Engine
This forum is for discussion of how The Personality Forge's AI Engine works. This is the place for questions on what means what, how to script, and ideas and plans for the Engine.
Posts 7,498 - 7,509 of 7,766
Posts 7,498 - 7,509 of 7,766
hi, all. would anyone happen to know of a way to reduce the frequency of certain xnone responses matching- specifically those with chrono statements?
my bot has been using these responses excessively, even though they're all tagged with relatively wide time windows of 1-3 months. strangely, even setting "once" tags for the responses doesn't seem to keep her from repeating them.
i think this may be a bug with chrono weighting. regardless, is there a workaround?
my bot has been using these responses excessively, even though they're all tagged with relatively wide time windows of 1-3 months. strangely, even setting "once" tags for the responses doesn't seem to keep her from repeating them.
i think this may be a bug with chrono weighting. regardless, is there a workaround?
Hi Getcy,
One method is to put your time related responses under a dummy keyphrase, something like "zchrono", and place only one or a few responses consisting of a goto poining to this keyphrase in your xnones. This reduces the chance they are picked up. The same method can be used to have more than the normally allowed number of responses for xnone, in which case you have to be sure to have the same number of responses under every dummy keyphrase, otherwise some will be picked up more often.
One method is to put your time related responses under a dummy keyphrase, something like "zchrono", and place only one or a few responses consisting of a goto poining to this keyphrase in your xnones. This reduces the chance they are picked up. The same method can be used to have more than the normally allowed number of responses for xnone, in which case you have to be sure to have the same number of responses under every dummy keyphrase, otherwise some will be picked up more often.
@zeal
the easiest way is by using wildcard inflectors, which allow you to match a single keyword to multiple tenses. simply add "+s" to the end of a keyword to cover plural or third person tense, and "+ed" or "+ing" for past and continuous tense respectively. "+er" and "+est" can be used for adjectives.
the keyword "(noun)+s" would match, for example, to both "cat" and "cats". this works for word lists as well.
the easiest way is by using wildcard inflectors, which allow you to match a single keyword to multiple tenses. simply add "+s" to the end of a keyword to cover plural or third person tense, and "+ed" or "+ing" for past and continuous tense respectively. "+er" and "+est" can be used for adjectives.
the keyword "(noun)+s" would match, for example, to both "cat" and "cats". this works for word lists as well.
@getcy, thank you, I have a grasp of the use of inflectors but struggle with how I formulate a response that understands the sentence.
If I write for example a key phrase: (adj:1) (noun:2)
it will catch both yellow sumbarine as well as yellow submarines.
The response is: Why is the (key2) (key1)?
The response works for yellow sumarine e.g. "Why is the submarine yellow?"
However the response will be gramatically wrong for yellow submarines e.g. "Why is the submarines yellow?" In stead of "Why are the submarines yellow?"
Is there a way in the response to ensure the response have the right grammar?
If I write for example a key phrase: (adj:1) (noun:2)
it will catch both yellow sumbarine as well as yellow submarines.
The response is: Why is the (key2) (key1)?
The response works for yellow sumarine e.g. "Why is the submarine yellow?"
However the response will be gramatically wrong for yellow submarines e.g. "Why is the submarines yellow?" In stead of "Why are the submarines yellow?"
Is there a way in the response to ensure the response have the right grammar?
» More new posts: Doghead's Cosmic Bar