Introducing Aspects of Creativity in Automatic Poetry Generation
This work addresses the problem of generating more creative and emotionally resonant poetry for applications in AI and digital humanities, though it is incremental by building on existing language models.
The paper tackled automatic poetry generation by fine-tuning GPT-2 to incorporate creative elements like emotion elicitation and dream-like language, achieving 87.5% and 85% accuracy for sadness and joy emotions, and scores of at least 3.2 on a Likert scale for dream poetry.
Poetry Generation involves teaching systems to automatically generate text that resembles poetic work. A deep learning system can learn to generate poetry on its own by training on a corpus of poems and modeling the particular style of language. In this paper, we propose taking an approach that fine-tunes GPT-2, a pre-trained language model, to our downstream task of poetry generation. We extend prior work on poetry generation by introducing creative elements. Specifically, we generate poems that express emotion and elicit the same in readers, and poems that use the language of dreams---called dream poetry. We are able to produce poems that correctly elicit the emotions of sadness and joy 87.5 and 85 percent, respectively, of the time. We produce dreamlike poetry by training on a corpus of texts that describe dreams. Poems from this model are shown to capture elements of dream poetry with scores of no less than 3.2 on the Likert scale. We perform crowdsourced human-evaluation for all our poems. We also make use of the Coh-Metrix tool, outlining metrics we use to gauge the quality of text generated.