A prototype system for playing a minimal improvisational game with one or more human or computer players is discussed. The game, Chain Reaction, has players collectively build a chain of word pairs or solid compounds. With a basis in oral culture, it emphasizes memory and rapid improvisation. Chains are only locally coherent, so absurdity and humor increases during play. While it is trivial to develop a computer player using textual corpora and literature-culture concepts, our approach is unique in that we have grounded our work in the principles of oral culture according to Walter Ong, an early scholar of orature. We show how a simple computer model can be designed to embody many aspects of oral poetics as theorized by Ong, suggesting design directions for other work in oral improvisation and poetics. The opportunities for own our system’s further development include creating culturally specific automated players and situating play in different temporal, physical, and social contexts.

Novels and short stories are not just remarkable because of what events they represent. The narrative style they employ is significant. To understand the specific contributions of different aspects of this style, it is possible to create limited symbolic models of narrating that hold almost all of the narrative discourse constant while varying a single aspect. In this paper we use a new implementation of a system for narrative discourse generation, Curveship, to change how existents at the story level are named. This by itself allows for the telling of the same underlying story in ways that evoke, for instance, a fabular or parable-like mode, the style of narrator Patrick Bateman in Brett Easton Ellis’s American Psycho, and the unusual dialect of Anthony Burgess’s A Clockwork Orange.