Let's FACE it. Finnish Poetry Generation with Aesthetics and Framing
This addresses the challenge of generating creative poetry in morphologically rich Finnish, though it appears incremental as it builds on existing master-apprentice and genetic algorithm paradigms.
The authors tackled Finnish poetry generation by developing a genetic algorithm that teaches a BRNN model to create poems, incorporating aesthetic features like sonic patterns and metaphor in the fitness function. They achieved evaluation through both automatic metrics and human assessment of aesthetics and creativity.
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.