urbazewski's Journal: beat geek

I'm including a comment I made in the discussion of Kurzweil's poetry generator in hopes of getting more feedback. Thanks!

-------------------

I've been working on a project (nicknamed "beat geek" in my head) that uses the digital equivalents of dada/beat cut-up techniques and other forms of randomness in or artificial generation of language.

For example, I have a program called autopoem (written by Bill Sethares) loosely based on an idea from Shannon's original paper on information theory.

Suppose you took all the words in the English language and calculated how often the character "s" is followed by the character "t", the character "e", and so on. You'd end with a table of transition probabilities that showed how often each letter is followed by any other letter (or punctuation mark or space) and starting with a single seed letter you could generate "english-like" words randomly. The output using the probability that a single letter is followed by another letter doesn't actually resemble English much, nor does the output using probabilities based on two letter combinations (how often is "th" followed by "e", by "a", and so on) but by the time you get to 3 letter combinations, (how often is "the" followed by "a" or by "s") the output starts to look a lot like "twas brillig and the slithy toves", like ye olde englishe with very creative spelling.

The scheme I described above is difficult to implement in practice, because the table of probabilities gets big fast as the number of letters used to determine the next letter gets longer. Autopoem uses a particular text as a source and instead of generating a table of probabilities it scans the text looking for the next of the letter sequence, say "the", and then selects whatever letter or punctuation mark comes next, say "a", then it continues scanning until it finds the next occurrence of "hea", and selects the following letter, and so on. the longer the sequence of letters, the more likely it is that whole words or phrases from the original text will appear in the output. An alternative version, requiring a reasonably long text, applies the same principle on the word level, how often is the word "red" followed by the word "hat" or "dog" or so on.

Here's some autopoem output:

Your strip of entirely
tired witches scarecrow me at night
That reached the next
He witches at and glow in a cruel head
Done behind the mark

Nothing but the Land of blue
And the green wizard answer with sharp teeth

(anyone care to guess the source text?)

Other ideas/algorithms/programs that fall into the same genre are dilbert's corporate values generator (now defunct?), eliza (especially when she interacts with zippy), madlibs (I don't know of a computer application), scott reynen's poetry and prose generators, rob malda's poetry generator (currently offline) & googlism.

Any suggestions or links to related ideas or programs would be greatly appreciated --- anything having to do with language generated digitally would be of interest.

Some related things

[bj8rn]

The first thing that comes to my mind is the Postmodernism Generator [monash.edu.au], which is based on the Dada Engine [null.org]. May be worth checking out as examples.

Someone mentioned Markov chains in the comments. In connection to this, generative grammars (mostly associated with Noam Chomsky) may be of interest to you. I say may, as the term seems to be awfully wide these days and I'm not sure if it means what I though it means anymore. But Markov chains and generative grammars seem to be quite popular in generating music and

How many Quatloos do I win?

[sporktoast]

I'm guessing the source text is an excerpt from the first OZ book. witches, scarecrow, Land, wizard, and green all seem to suggest it.

On a not unrelated note, have you read Wicked: The Life and Times of the Wicked Witch of the West [amazon.com], by Gregory Maguire?

The first OZ book as told from the Wicked Witch's perspective. Very clever, and not just satisfied with being merely that. He did a great job of creating an adult world beyond the childrens' view of the original stories. I've heard its being made into a

Re:How many Quatloos do I win?

[urbazewski]

I loved Wicked, I read it fairly recently in conjunction with The Wizard of OZ, which, surprisingly, I didn't find very good at all.

A friend just sent me a link to the website for the Broadway musical:

Wicked website [musicalschwartz.com]

I read a bunch of paired books last year: the new translation of Beowulf by Seamus Heaney and Grendel by John Gardner, both excellent; Mrs. Dalloway by Virginia Woolf and The Hours by Michael Cunningham, the latter suffered a bit from the comparison; and The Odyssey translated by Richard Lat

Re:How many Quatloos do I win?

[sporktoast]

I read Wicked about a year ago, not in conjunction with, but closely followed by The Wizard of OZ. I had about the same reaction as you.

Some childrens books retain the embers of thier magic into the reader's adulthood where they can be easily rekindled with a rereading. This one just snuffed right out for me. I felt betrayed by the matter-of-fact, even slightly giddy, wholesale dispatching of every obstacle in our heroes' ways. It seemed not so much sadistic as just unthinking. I'm sure much of it was

Re:How many Quatloos do I win?

[urbazewski]

I haven't read any of Maguire's other books, but I highly recommend Ella Enchanted by Gail Carson Levine. It's a young adult book, a very quick read, but it gives a really nice perspective on Cinderella, like how exactly can Cinderella's stepsisters push her around like that? And how many fairy godmothers are there? In the kids' books that adults will love department I'd also recommend Haroun and the Sea of Stories by Salman Rushdie.

Bill (my spouse) read Confessions of an Ugly Step Sister and thought it w