Enhancing Topic-to-Essay Generation with External Commonsense Knowledge

Pengcheng Yang, Lei Li, Fuli Luo, Tianyu Liu, Xu Sun


Abstract
Automatic topic-to-essay generation is a challenging task since it requires generating novel, diverse, and topic-consistent paragraph-level text with a set of topics as input. Previous work tends to perform essay generation based solely on the given topics while ignoring massive commonsense knowledge. However, this commonsense knowledge provides additional background information, which can help to generate essays that are more novel and diverse. Towards filling this gap, we propose to integrate commonsense from the external knowledge base into the generator through dynamic memory mechanism. Besides, the adversarial training based on a multi-label discriminator is employed to further improve topic-consistency. We also develop a series of automatic evaluation metrics to comprehensively assess the quality of the generated essay. Experiments show that with external commonsense knowledge and adversarial training, the generated essays are more novel, diverse, and topic-consistent than existing methods in terms of both automatic and human evaluation.
Anthology ID:
P19-1193
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2002–2012
URL:
https://www.aclweb.org/anthology/P19-1193
DOI:
10.18653/v1/P19-1193
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
https://www.aclweb.org/anthology/P19-1193.pdf