System Supporting Poetry Generation Using Text Generation and Style Transfer Methods

Abstract

The paper presents the Bairon system that supports the automatic generation of poetry. The proposed system allows generating a poem in the literary style of the selected writer using the user's input as the first line, and translating the given text into Shakespearean English. To accomplish that, GPT-2 and T5 language models were fine-tuned. We also propose easy to understand metrics to evaluate the quality of the generated poems and their similarity to the corresponding poet's original work, and to present the results. Additionally, the Poetry Turing Test with human participants was conducted to get another measure of quality of the generated poetry.