There Once Was a Really Bad Poet, It Was Automated but You Didn't Know It
This work addresses the specific problem of generating high-quality limericks for applications in creative AI, though it is incremental as it builds on existing poetry generation methods.
The authors tackled the challenge of automated limerick generation, which requires strict poetic constraints and coherent storytelling, by introducing LimGen, a system that outperforms both neural network-based and rule-based poetry models.
Limerick generation exemplifies some of the most difficult challenges faced in poetry generation, as the poems must tell a story in only five lines, with constraints on rhyme, stress, and meter. To address these challenges, we introduce LimGen, a novel and fully automated system for limerick generation that outperforms state-of-the-art neural network-based poetry models, as well as prior rule-based poetry models. LimGen consists of three important pieces: the Adaptive Multi-Templated Constraint algorithm that constrains our search to the space of realistic poems, the Multi-Templated Beam Search algorithm which searches efficiently through the space, and the probabilistic Storyline algorithm that provides coherent storylines related to a user-provided prompt word. The resulting limericks satisfy poetic constraints and have thematically coherent storylines, which are sometimes even funny (when we are lucky).