A Flexible Integrated Architecture For Generating Poetic Texts

Abstract

In this paper we describe a flexible approach to natural language generation that employs a stochastic hillclimbing search algorithm and an integrated architecture. We then discuss the benefits of this approach over existing, informative, goal-driven generation systems. We choose the generation of poetry as our research task domain, as it is a prime example of natural language that demands the degree of flexibility provided by our approach. Finally, we report and discuss results of our preliminary implementation work.