skip to main content
10.1145/3483529.3483537acmotherconferencesArticle/Chapter ViewAbstractPublication PagesartechConference Proceedingsconference-collections
research-article

Imitations of Immortality: Learning from Human Imitative Examples in Transformer Poetry Generation

Published: 20 February 2022 Publication History

Abstract

Learning to generate poetry in the style of the poet can make models style experts, but humans who create imitative works take a more general approach that incorporates knowledge outside the poet's style. Instead of learning from a large corpus of one poet's works, can machines imitate deep style using only one example of her work? To explore generating poetic variations for a web-based installation art work, I wrote eight poems that imitated the structure of eight poets, and used them to fine tune a transformer model that has seen only one poem by each author. The poems presented show structures borrowing from the human imitation in addition to prompted content of the original, suggesting the model has learned aspects of how humans write variations on content by imitating style. Audience evaluation reveals an ability for machine-generated text to reproduce the nuance of the original text as well as the human variation, despite being less expressive.

References

[1]
Brendan Bena and Jugal Kalita. 2020. Introducing Aspects of Creativity in Automatic Poetry Generation. arXiv:2002.02511 [cs] (February 2020). Retrieved October 5, 2020 from http://arxiv.org/abs/2002.02511
[2]
Gwern Branwen. 2019. GPT-2 Neural Network Poetry. (March 2019). Retrieved January 19, 2021 from https://www.gwern.net/GPT-2
[3]
Ondřej Dušek and Zdeněk Kasner. 2020. Evaluating Semantic Accuracy of Data-to-Text Generation with Natural Language Inference. arXiv:2011.10819 [cs] (November 2020). Retrieved January 14, 2021 from http://arxiv.org/abs/2011.10819
[4]
Zhenxin Fu, Xiaoye Tan, Nanyun Peng, Dongyan Zhao, and Rui Yan. 2017. Style Transfer in Text: Exploration and Evaluation. arXiv:1711.06861 [cs] (November 2017). Retrieved October 8, 2020 from http://arxiv.org/abs/1711.06861
[5]
Nils Kobis and Luca Mossink. 2020. Artificial Intelligence versus Maya Angelou: Experimental evidence that people cannot differentiate AI-generated from human-written poetry. arXiv.org. Retrieved October 5, 2020 from https://econpapers.repec.org/paper/arxpapers/2005.09980.htm
[6]
Sharon Levy, Michael Saxon, and William Yang Wang. 2021. The Truth is Out There: Investigating Conspiracy Theories in Text Generation. arXiv:2101.00379 [cs] (January 2021). Retrieved January 19, 2021 from http://arxiv.org/abs/2101.00379
[7]
Piji Li, Haisong Zhang, Xiaojiang Liu, and Shuming Shi. 2020. Rigid Formats Controlled Text Generation. arXiv:2004.08022 [cs] (April 2020). Retrieved October 5, 2020 from http://arxiv.org/abs/2004.08022
[8]
Yi Liao, Yasheng Wang, Qun Liu, and Xin Jiang. 2019. GPT-based Generation for Classical Chinese Poetry. arXiv:1907.00151 [cs] (September 2019). Retrieved October 5, 2020 from http://arxiv.org/abs/1907.00151
[9]
M. C. Santillan and A. P. Azcarraga. 2020. Poem Generation using Transformers and Doc2Vec Embeddings. In 2020 International Joint Conference on Neural Networks (IJCNN), 1–7. https://doi.org/10.1109/IJCNN48605.2020.9207442
[10]
Irene Solaiman, Miles Brundage, Jack Clark, Amanda Askell, Ariel Herbert-Voss, Jeff Wu, Alec Radford, Gretchen Krueger, Jong Wook Kim, Sarah Kreps, Miles McCain, Alex Newhouse, Jason Blazakis, Kris McGuffie, and Jasmine Wang. 2019. Release Strategies and the Social Impacts of Language Models. arXiv:1908.09203 [cs] (November 2019). Retrieved October 6, 2020 from http://arxiv.org/abs/1908.09203
[11]
Amanda Stent, Matthew Marge, and Mohit Singhai. 2005. Evaluating Evaluation Methods for Generation in the Presence of Variation. In Computational Linguistics and Intelligent Text Processing (Lecture Notes in Computer Science), Springer, Berlin, Heidelberg, 341–351. https://doi.org/10.1007/978-3-540-30586-6_38
[12]
Muminov Ibrokhim Botir Ugli. 2020. Will Human Beings Be Superseded by Generative Pre-trained Transformer 3 (GPT-3) in Programming? IJOT 2, 10 (October 2020), 141–143. https://doi.org/10.31149/ijot.v2i10.769
[13]
Jia Wei, Qiang Zhou, and Yici Cai. 2018. Poet-based Poetry Generation: Controlling Personal Style with Recurrent Neural Networks. In 2018 International Conference on Computing, Networking and Communications (ICNC), 156–160.

Cited By

View all
  • (2024)TIME ENOUGH: Generative AI Visions of Climate Change as Cave Paintings of the FutureProceedings of the 16th Conference on Creativity & Cognition10.1145/3635636.3672190(608-613)Online publication date: 23-Jun-2024
  • (2024)When Teams Embrace AI: Human Collaboration Strategies in Generative Prompting in a Creative Design TaskProceedings of the 2024 CHI Conference on Human Factors in Computing Systems10.1145/3613904.3642133(1-14)Online publication date: 11-May-2024
  • (2023)Does human–AI collaboration lead to more creative art? Aesthetic evaluation of human-made and AI-generated haiku poetryComputers in Human Behavior10.1016/j.chb.2022.107502139:COnline publication date: 1-Feb-2023

Index Terms

  1. Imitations of Immortality: Learning from Human Imitative Examples in Transformer Poetry Generation
              Index terms have been assigned to the content through auto-classification.

              Recommendations

              Comments

              Information & Contributors

              Information

              Published In

              cover image ACM Other conferences
              ARTECH '21: Proceedings of the 10th International Conference on Digital and Interactive Arts
              October 2021
              761 pages
              Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

              Publisher

              Association for Computing Machinery

              New York, NY, United States

              Publication History

              Published: 20 February 2022

              Permissions

              Request permissions for this article.

              Check for updates

              Qualifiers

              • Research-article
              • Research
              • Refereed limited

              Conference

              ARTECH 2021

              Acceptance Rates

              Overall Acceptance Rate 128 of 238 submissions, 54%

              Contributors

              Other Metrics

              Bibliometrics & Citations

              Bibliometrics

              Article Metrics

              • Downloads (Last 12 months)32
              • Downloads (Last 6 weeks)2
              Reflects downloads up to 18 Feb 2025

              Other Metrics

              Citations

              Cited By

              View all
              • (2024)TIME ENOUGH: Generative AI Visions of Climate Change as Cave Paintings of the FutureProceedings of the 16th Conference on Creativity & Cognition10.1145/3635636.3672190(608-613)Online publication date: 23-Jun-2024
              • (2024)When Teams Embrace AI: Human Collaboration Strategies in Generative Prompting in a Creative Design TaskProceedings of the 2024 CHI Conference on Human Factors in Computing Systems10.1145/3613904.3642133(1-14)Online publication date: 11-May-2024
              • (2023)Does human–AI collaboration lead to more creative art? Aesthetic evaluation of human-made and AI-generated haiku poetryComputers in Human Behavior10.1016/j.chb.2022.107502139:COnline publication date: 1-Feb-2023

              View Options

              Login options

              View options

              PDF

              View or Download as a PDF file.

              PDF

              eReader

              View online with eReader.

              eReader

              HTML Format

              View this article in HTML Format.

              HTML Format

              Figures

              Tables

              Media

              Share

              Share

              Share this Publication link

              Share on social media