Skip to main content

The Mechanical Bard: An Interpretable Machine Learning Approach to Shakespearean Sonnet Generation

Publication ,  Conference
Agnew, E; Qiu, M; Zhu, L; Wiseman, S; Rudin, C
Published in: Proceedings of the Annual Meeting of the Association for Computational Linguistics
January 1, 2023

We consider the automated generation of sonnets, a poetic form constrained according to meter, rhyme scheme, and length. Sonnets generally also use rhetorical figures, expressive language, and a consistent theme or narrative. Our constrained decoding approach allows for the generation of sonnets within preset poetic constraints, while using a relatively modest neural backbone. Human evaluation confirms that our approach produces Shakespearean sonnets that resemble human-authored sonnets, and which adhere to the genre’s defined constraints and contain lyrical language and literary devices.

Duke Scholars

Published In

Proceedings of the Annual Meeting of the Association for Computational Linguistics

ISSN

0736-587X

Publication Date

January 1, 2023

Volume

2

Start / End Page

1627 / 1638
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Agnew, E., Qiu, M., Zhu, L., Wiseman, S., & Rudin, C. (2023). The Mechanical Bard: An Interpretable Machine Learning Approach to Shakespearean Sonnet Generation. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (Vol. 2, pp. 1627–1638).
Agnew, E., M. Qiu, L. Zhu, S. Wiseman, and C. Rudin. “The Mechanical Bard: An Interpretable Machine Learning Approach to Shakespearean Sonnet Generation.” In Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2:1627–38, 2023.
Agnew E, Qiu M, Zhu L, Wiseman S, Rudin C. The Mechanical Bard: An Interpretable Machine Learning Approach to Shakespearean Sonnet Generation. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics. 2023. p. 1627–38.
Agnew, E., et al. “The Mechanical Bard: An Interpretable Machine Learning Approach to Shakespearean Sonnet Generation.” Proceedings of the Annual Meeting of the Association for Computational Linguistics, vol. 2, 2023, pp. 1627–38.
Agnew E, Qiu M, Zhu L, Wiseman S, Rudin C. The Mechanical Bard: An Interpretable Machine Learning Approach to Shakespearean Sonnet Generation. Proceedings of the Annual Meeting of the Association for Computational Linguistics. 2023. p. 1627–1638.

Published In

Proceedings of the Annual Meeting of the Association for Computational Linguistics

ISSN

0736-587X

Publication Date

January 1, 2023

Volume

2

Start / End Page

1627 / 1638