In this paper we compare various text generation models' ability to write poetry in the style of early English Romanticism. These models include: Character-Level Recurrent Neural Networks with Long Short-Term Memory, Hugging Face's GPT-2, OpenAI's GPT-3, and EleutherAI's GPT-NEO. Quality was measured based syllable count and coherence with the automatic evaluation metric GRUEN. Character-Level Recurrent Neural Networks performed far worse compared to transformer models. And, as parameter-size increased, the quality of transformer models' poems improved. These models are typically not compared in a creative context, and we are happy to contribute.
Cite
@article{arxiv.2206.11864,
title = {Romantic-Computing},
author = {Elizabeth Horishny},
journal= {arXiv preprint arXiv:2206.11864},
year = {2022}
}