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

Edwin Agnew, Michelle Qiu, Lily Zhu, Sam Wiseman, Cynthia Rudin


Abstract
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.
Anthology ID:
2023.acl-short.140
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1627–1638
Language:
URL:
https://aclanthology.org/2023.acl-short.140
DOI:
10.18653/v1/2023.acl-short.140
Award:
 Outstanding Paper Award
Bibkey:
Cite (ACL):
Edwin Agnew, Michelle Qiu, Lily Zhu, Sam Wiseman, and Cynthia Rudin. 2023. The Mechanical Bard: An Interpretable Machine Learning Approach to Shakespearean Sonnet Generation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1627–1638, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
The Mechanical Bard: An Interpretable Machine Learning Approach to Shakespearean Sonnet Generation (Agnew et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-short.140.pdf
Video:
 https://aclanthology.org/2023.acl-short.140.mp4