From Shakespeare to Li-Bai: Adapting a Sonnet Model to Chinese Poetry

Zhuohan Xie, Jey Han Lau, Trevor Cohn


Abstract
In this paper, we adapt Deep-speare, a joint neural network model for English sonnets, to Chinese poetry. We illustrate characteristics of Chinese quatrain and explain our architecture as well as training and generation procedure, which differs from Shakespeare sonnets in several aspects. We analyse the generated poetry and find that model works well for Chinese poetry, as it can: (1) generate coherent 4-line quatrains of different topics; and (2) capture rhyme automatically (to a certain extent).
Anthology ID:
U19-1002
Volume:
Proceedings of the 17th Annual Workshop of the Australasian Language Technology Association
Month:
4--6 December
Year:
2019
Address:
Sydney, Australia
Editors:
Meladel Mistica, Massimo Piccardi, Andrew MacKinlay
Venue:
ALTA
SIG:
Publisher:
Australasian Language Technology Association
Note:
Pages:
10–18
Language:
URL:
https://aclanthology.org/U19-1002
DOI:
Bibkey:
Cite (ACL):
Zhuohan Xie, Jey Han Lau, and Trevor Cohn. 2019. From Shakespeare to Li-Bai: Adapting a Sonnet Model to Chinese Poetry. In Proceedings of the 17th Annual Workshop of the Australasian Language Technology Association, pages 10–18, Sydney, Australia. Australasian Language Technology Association.
Cite (Informal):
From Shakespeare to Li-Bai: Adapting a Sonnet Model to Chinese Poetry (Xie et al., ALTA 2019)
Copy Citation:
PDF:
https://aclanthology.org/U19-1002.pdf