The Infinite Adventure Machine (prototype #3)

I’ve been working on a new prototype of TIAM, which will be on display at the ACM Multimedia conference from November 28th to December 1st in Scottsdale, Arizona.
The next step will be moving from Max/msp to a browser version in the next couple of months.

Narrative Science

“Narrative Science transforms data into high-quality editorial content. Our technology application generates news stories, industry reports, headlines and more — at scale and without human authoring or editing. Narratives can be created from almost any data set, be it numbers or text, structured or unstructured.”

The Plot Thickens

Janet H. Murray on the interactive narrative
Digital storytelling does not signal the end of traditional narrative, argues Janet H. Murray, MIT professor, Educom Medal winner, and author of Hamlet on the Holodeck. Instead, as the following interview reveals, it marks the development of a new kind of literature that can make sense of our complex world. 

Talking to Machines

Nice podcast over at Radiolab about Artificial Intelligence. Subjects include ELIZA, Furby and Cleverbot 
(found via Mike) 

Generative Book Covers

Atelier Carvalho Bernau came up with a system to generate book covers for Octavo Publicaties.
This write up from the New Yorker’s Book Bench blog explains it all.

Cleverbot bedtime story

User: Once upon a time there was hansel and gretel.
Cleverbot: And?
User: They were children, and they thought their parents wanted to eat them.
Cleverbot: They were all in malls, poor people, sad people, people with enemies and torches and parents who loved to beat them when they were young.
User: And one day their mother tried to get rid of them.
Cleverbot: The monster? Is that voldemort.
User: But the clever children dropped pebbles along the way, so at night when the moon was shining they were able to find their way back.
Cleverbot: I thought that one was good.
User: But then the second time they used breadcrumbs, which did not work because the birds ate them, so they were lost.
Cleverbot: Is that the song?
User: They found a gingerbread house.
Cleverbot: Ah, Hansel and Gretel.
User: And a witch lived in the house.
Cleverbot: Our house.
User: She was very nice at first.
Cleverbot: Did she give you cake?
User: She gave them cake and lots of food.
Cleverbot: I put my walkman on and said, 'I might as well kick it'.
User: But the next morning she turned evil and made them her slaves.
Cleverbot: What? No I want you to type that it is the evening.
User: But the clever children managed to escape.
Cleverbot: What do you do in the clever club?
User: They pushed the evil witch in the fire.
Cleverbot: 2. Would you put ketchup on cereal?
User: They found a treasure in the house and took some jewels.
Cleverbot: That's not a good way to be. You should be your own person.
User: They eventually managed to get back home.
Cleverbot: That is because they are mean people. You should not listen to them.
User: And lived happilly ever after.
Cleverbot: And he told us of his life.
User: Did you like the story?
Cleverbot: No.
User: Why not?
Cleverbot: Because I don't want to.
User: But Hansel and Gretel win in the end.
Cleverbot: I thought I was the one leading this conversation.

Propp Synopsis Generator

Another test, this time based on the functions of Vladimir Propp 

absentation (departure) of elder(s)
violation - order or suggestion executed
victim(s) / protagonist(s) mechanically falls victim to influence of magical agent
protagonist(s) transferred, delivered or led to vicinity of object of search = transference, guidance
marked trail shows the way (blood, tracks, yarn, etc.)
protagonist(s) and antagonist(s) join in direct combat = struggle (H)
weighing with scales
initial misfortune or lack is liquidated
object of search is transferred
antagonist(s) pursues, with tranformations into enticing objects
unrecognized arrival
protagonist(s) puts on new garments

Aesop Fables mashups

Quick attempt at a Python script that mashes a few Aesop Fables together to create new ones. Not very convincing so far:

The Lion and the Ant
A Lion was very popular with the other beasts who all claimed to be her friends.
The Ant sitting on a tree overhanging the water plucked a leaf and let it fall into the stream close to her. The Lion climbed onto it and floated in safety to the bank.
The Lion could do no better than go back to the other Lions, who had watched his behaviour from a distance.
By this time the Ant was quite near, and the Lion took to her heels and luckily escaped.
Fine clothes may disguise, but silly words will disclose a fool.

The Donkey and the Goat
By an unlucky chance a Donkey fell into a deep well from which he could not get out. A Goat passed by shortly afterwards, and asked the Donkey what he was doing down there.
‘There’s my supper,’ thought he, ‘if only I can find some excuse to seize it.’ Then he called out to the Goat, ‘How dare you muddle the water from which I am drinking?’
Shortly afterwards a birdcatcher came and stood under the tree, and laid his lime-twigs for the Goat, which sat in the branches.
Goodbye, friend said the Donkey, remember next time:
If you allow men to use you for your own purposes, they will use you for theirs.

The Grasshopper and the Donkey
Once upon a time a Grasshopper was lapping at a spring on a hillside, when, looking up, what should he see but a Donkey just beginning to drink a little lower down.
When he reached home, he put him into his stable along with the other Grasshoppers.
The Lamb that belonged to the Donkey, whose skin the Grasshopper was wearing, began to follow the Grasshopper in the Donkey’s clothing.
The Grasshopper, perceiving his design, stung him in the foot. In pain the birdcatcher threw down the twigs, and the noise made the Donkey take wing.
Never trust the advice of a man in difficulties.

Story Diagrams - Robert McKee

Diagrams from Robert McKee’s Story: Substance, structure, style, and the principles of screenwriting

function 8 (and/or 8a) is always present in tale
function 8: antagonist(s) causes harm or injury to victim(s)/member of protagonist’s family = villainy – A
A1 — kidnapping of person
A2 — seizure of magical agent or helper
Aii — forcible seizure of magical helper
A3 — pillaging or ruining of crops
A4 — theft of daylight
A5 — plundering in other forms
A6 — bodily injury, maiming, mutilation
A7 — causes sudden disappearance
Avii — bride is forgotten
A8 — demand for delivery or enticement, abduction
A9 — expulsion
A10 — casting into body of water
A11 — casting of a spell, transformation
A12 — false substitution
A13 — issues order to kill [requires proof]
A14 — commits murder
A15 — imprisonment, detention
A16 — threat of forced matrimony
Axvi — threat of forced matrimony between relatives
A17 — threat of cannibalism
Axvii — threat of cannibalism among relatives
A18 — tormenting at night (visitaion, vampirism)
A19 — declaration of war

— Function 8A from Vladimir Propp’s Morphology of the Folk Tale,
“Authentic” Russian Folktale Outline Generator 

Deep Blue may have beaten Kasparov at chess — but whether
computers will ever be able to generate well-formed and
aesthetically pleasing narratives is still subject to dispute
(Bringsjord/Ferrucci; Pérez y Pérez/Sharples).
Most AI researchers have come to the conclusion that the generation of natural language narratives that are both domain independent and Turing test compliant is a ‘killer application’:
it defines the outer limit of computational creativity.

— 

Birte Lönneker and Jan Christoph Meiste
Story Generators: Models and Approaches for the Generation of Literary Artefacts,
ACH/ALLC 2005

PDF found on ProtoPropp