Generating Classical Chinese Poems via Conditional Variational Autoencoder and Adversarial Training

Juntao Li, Yan Song, Haisong Zhang, Dongmin Chen, Shuming Shi, Dongyan Zhao, Rui Yan


Abstract
It is a challenging task to automatically compose poems with not only fluent expressions but also aesthetic wording. Although much attention has been paid to this task and promising progress is made, there exist notable gaps between automatically generated ones with those created by humans, especially on the aspects of term novelty and thematic consistency. Towards filling the gap, in this paper, we propose a conditional variational autoencoder with adversarial training for classical Chinese poem generation, where the autoencoder part generates poems with novel terms and a discriminator is applied to adversarially learn their thematic consistency with their titles. Experimental results on a large poetry corpus confirm the validity and effectiveness of our model, where its automatic and human evaluation scores outperform existing models.
Anthology ID:
D18-1423
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3890–3900
URL:
https://www.aclweb.org/anthology/D18-1423
DOI:
10.18653/v1/D18-1423
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
https://www.aclweb.org/anthology/D18-1423.pdf