Story Generation After TALE-SPIN

Abstract

TALE-SPIN, the laat major AI attempt at atory generation, approached the problem of making up atoriea primarily from the perspective of an impartial world simulator. AUTHOR ia a program (under development) which generates atoriea as a creative reaaoner in purauit of her own narrative goals. It is thus intended to aimulate an author's mind aa ahe makes up a story, rather than the world as things happen in it. The four major forces driving the atory generation process, according to the AUTHOR model, are (1) author intentionality, (2) conceptual reformulation, (3) reminding, and (4) the opportunity enhancement metagoal. 1. World Simulation Based Story Generation TALE-SPIN [Meehan, 1976] is a program which made up Aesop-fable-like conceptual atoriea, which it then expressed in natural language. Each atory TALE-SPIN made up waa based on a model of the storyworld, including the characters in it and their goala, peraonalities, and interperaonal relatione. Storiea were apun by working out consequences of the model. Thus, central to TALE-SPIN waa the idea of world simulation. The three levels TALE-SPIN was most concerned with simulating were: 1. character intentionality- e.g., if Joe Bear was hungry, he would try to get something to eat 2. social conatrainta- e.g., if Joe Bear believed Irving Bird to be hia friend, he could aak an outright favor; if Joe Bear believed their relation to be a bit cooler, he would feel obliged to offer something in return (auch aa a worm) 3. phyaical cauaality- e.g., if Irving Bird ate a worm, the worm would cease to exist; after "fooling around", Aa oppoaed to Sheldon Klein's ayetem which only produced atory texts and which ia incapable, in principle, of understanding the atoriea it "makes up " [Klein et el., 1976].