Automatic Poetry Generation from Prosaic Text

Tim Van de Cruys


Abstract
In the last few years, a number of successful approaches have emerged that are able to adequately model various aspects of natural language. In particular, language models based on neural networks have improved the state of the art with regard to predictive language modeling, while topic models are successful at capturing clear-cut, semantic dimensions. In this paper, we will explore how these approaches can be adapted and combined to model the linguistic and literary aspects needed for poetry generation. The system is exclusively trained on standard, non-poetic text, and its output is constrained in order to confer a poetic character to the generated verse. The framework is applied to the generation of poems in both English and French, and is equally evaluated for both languages. Even though it only uses standard, non-poetic text as input, the system yields state of the art results for poetry generation.
Anthology ID:
2020.acl-main.223
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2471–2480
Language:
URL:
https://aclanthology.org/2020.acl-main.223
DOI:
10.18653/v1/2020.acl-main.223
Bibkey:
Cite (ACL):
Tim Van de Cruys. 2020. Automatic Poetry Generation from Prosaic Text. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2471–2480, Online. Association for Computational Linguistics.
Cite (Informal):
Automatic Poetry Generation from Prosaic Text (Van de Cruys, ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.223.pdf
Video:
 http://slideslive.com/38929130