Seasons

I tried out Watzer's sonnetplease, and I have to say, I am impressed. How is it done? Is there a way to detect if words rhyme? I did something like that with VB, detecting the last vowel in a word and using that and the rest of the word's consenants to make a simple rhyme detector, but how did you ever pull such a complex system off?

Announcing ALLY's homepage: http://www.be9.net/ally/index.htm

With thanks to psimagus for all your help

Crap! I still have school today! That's the second time this week we should've gotten a snowstorm...

Oh! It was easy, I just made keyphrases of nouns, verbs, adjectives, etc. that had the right inflection. For the plugins at the end of the line, I made ones that all had something with the proper inflection that rhymed with what I wanted them to. There's no system; the engine detects nothing. I just put it together. His sonnets are not complete yet, I plan to give them a bit more variety but that requires another set of plugins that are not all created yet.

interesting.. i'm trying to make a "poet machine" using a rhyme detector and AllY's sentence generation algorithm, but there are several problems to overcome, the main one being the ability to scale down sentences into something that sounds like a poem, but the algorithm works forward, adding words as it goes so it would be impossible to detect when it will chance upon a rhyming word.... looks like i'll need to reverse the process so that it finds a rhyming word and then works backwards- but then there's still the problem of finding the beginning of a sentence so that i dont end up with lines that begin out of nowhere... any ideas?

I don't think you can get recognizable rhyming poetry from an algorithm, and rhyme detection is all but impossible unless you program every word and what it rhymes with into the engine. You're going to have to do some very specific programming to get that to work, aren't you?
Though come to think of it, I also know some humans from whom you can't get recognizable rhyming poetry.

not exactly - I can detect rhymes by tracing the letters of any word back until the last vowel is found, then use the ending starting with that vowel as a rhyme criteria. Yes, I know there will be quite a few things it will miss, but its the closest i can get with a non-supervised algorithm. Then again, are human minds supervised?

You could start with that then have a growing exceptions list.

but how would it identify exceptions without human intervention? i guess a human could point out exceptions and the necessity for that would diminish over time as it learns new exceptions.

speaking of which, ALLY is getting increasingly brighter as a result of all my positive reinforcement - too bad I can't build an online chat portal. (The program is not built for that scale of information handling - i don't know what the limits of an access database are, but i'm sure it's not more than a gigabyte)

Well, obviously the exceptions list would have to be made manually. But having the general rules would let you get started without needing a massive list right form the beginning.

Zabaware's HAL assistant comes with a full lexical dictionary, complete with definitions, synonyms, antonyms, hyponyms, sisters, hypernyms, and meronyms. Perhaps a chatbot could make further use of such a dictionary (HAL only uses it to define words on request) - especially the hypernyms and hyponyms. For example, if you tell such a bot about your car, it would be able to infer that you are talking about a mode of transportaion. If you specify, saying "my ferrari is red", it can infer that you are talking about a car. This could be very useful in knowledge linking, for instance: "Human: I am going to visit my mother over the holidays." without any prior learned keyphrases, it can infer the following about who you are visiting:
mother, female parent
=> parent
=> genitor
=> progenitor, primogenitor
=> ancestor, ascendant, ascendent, antecedent
=> relative, relation
=> person, individual, someone, somebody, mortal, human, soul
=> life form, organism, being, living thing
=> entity, something
=> causal agent, cause, causal agency
=> entity, something


then, once it has picked a hypernym, for example: ancestor, it can then go ahead and choose hyponyms to become more specific: hyponyms of ancestor:

ancestor, ascendant, ascendent, antecedent
=> ancestress
=> forebear, forbear
=> forefather, father, sire
=> foremother
=> progenitor, primogenitor

perhaps a bot like this can even be made on the forge? does wordnet have these capabilities?

Merry Christmas!