Shall I Compare Thee to a Machine-Written Sonnet? An Approach to Algorithmic Sonnet Generation
This work addresses the problem of generating high-quality, human-like poetry for applications in creative AI and literary arts, representing a strong domain-specific advancement.
The paper tackled algorithmic sonnet generation by introducing novel elements like in-line punctuation and part-of-speech restrictions, resulting in poetry that won the 2018 PoetiX Literary Turing Test Award for its human-like qualities.
We provide an approach for generating beautiful poetry. Our sonnet-generation algorithm includes several novel elements that improve over the state of the art, leading to metrical, rhyming poetry with many human-like qualities. These novel elements include in-line punctuation, part of speech restrictions, and more appropriate training corpora. Our work is the winner of the 2018 PoetiX Literary Turing Test Award for computer-generated poetry.