Deep-speare: A joint neural model of poetic language, meter and rhyme

Jey Han Lau, Trevor Cohn, Timothy Baldwin, Julian Brooke, Adam Hammond


Abstract
In this paper, we propose a joint architecture that captures language, rhyme and meter for sonnet modelling. We assess the quality of generated poems using crowd and expert judgements. The stress and rhyme models perform very well, as generated poems are largely indistinguishable from human-written poems. Expert evaluation, however, reveals that a vanilla language model captures meter implicitly, and that machine-generated poems still underperform in terms of readability and emotion. Our research shows the importance expert evaluation for poetry generation, and that future research should look beyond rhyme/meter and focus on poetic language.
Anthology ID:
P18-1181
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1948–1958
Language:
URL:
https://aclanthology.org/P18-1181
DOI:
10.18653/v1/P18-1181
Bibkey:
Cite (ACL):
Jey Han Lau, Trevor Cohn, Timothy Baldwin, Julian Brooke, and Adam Hammond. 2018. Deep-speare: A joint neural model of poetic language, meter and rhyme. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1948–1958, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Deep-speare: A joint neural model of poetic language, meter and rhyme (Lau et al., ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-1181.pdf
Note:
 P18-1181.Notes.pdf
Presentation:
 P18-1181.Presentation.pdf
Video:
 https://aclanthology.org/P18-1181.mp4
Code
 jhlau/deepspeare