The Character Thinks Ahead: creative writing with deep learning nets and its stylistic assessment
This work addresses creative writing applications for AI, but it appears incremental as it focuses on stylistic assessment without broad SOTA claims.
The authors tackled the problem of controlling deep learning text models to generate contemporary poetry, specifically assessing whether their controls achieved stylistic distinctiveness in their work 'The Character Thinks Ahead' (2016/17).
We discuss how to control outputs from deep learning models of text corpora so as to create contemporary poetic works. We assess whether these controls are successful in the immediate sense of creating stylo- metric distinctiveness. The specific context is our piece The Character Thinks Ahead (2016/17); the potential applications are broad.