Let's FACE it. Finnish Poetry Generation with Aesthetics and Framing

TL;DR

This paper introduces a novel Finnish poetry generator that combines genetic algorithms and neural networks, incorporating aesthetic criteria and framing to produce creative and coherent poetry, validated through both automatic and human evaluations.

Contribution

It presents a new hybrid approach for morphologically rich language poetry generation, integrating aesthetic modeling within a genetic algorithm and neural network framework.

Findings

The system generates poetry with high aesthetic quality.

Automatic and human evaluations confirm the effectiveness of aesthetic modeling.

The approach advances computational creativity in morphologically complex languages.

Abstract

We present a creative poem generator for the morphologically rich Finnish language. Our method falls into the master-apprentice paradigm, where a computationally creative genetic algorithm teaches a BRNN model to generate poetry. We model several parts of poetic aesthetics in the fitness function of the genetic algorithm, such as sonic features, semantic coherence, imagery and metaphor. Furthermore, we justify the creativity of our method based on the FACE theory on computational creativity and take additional care in evaluating our system by automatic metrics for concepts together with human evaluation for aesthetics, framing and expressions.