Discourse-Aware Neural Rewards for Coherent Text Generation

Antoine Bosselut, Asli Celikyilmaz, Xiaodong He, Jianfeng Gao, Po-Sen Huang, Yejin Choi


Abstract
In this paper, we investigate the use of discourse-aware rewards with reinforcement learning to guide a model to generate long, coherent text. In particular, we propose to learn neural rewards to model cross-sentence ordering as a means to approximate desired discourse structure. Empirical results demonstrate that a generator trained with the learned reward produces more coherent and less repetitive text than models trained with cross-entropy or with reinforcement learning with commonly used scores as rewards.
Anthology ID:
N18-1016
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Marilyn Walker, Heng Ji, Amanda Stent
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
173–184
Language:
URL:
https://aclanthology.org/N18-1016
DOI:
10.18653/v1/N18-1016
Bibkey:
Cite (ACL):
Antoine Bosselut, Asli Celikyilmaz, Xiaodong He, Jianfeng Gao, Po-Sen Huang, and Yejin Choi. 2018. Discourse-Aware Neural Rewards for Coherent Text Generation. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 173–184, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Discourse-Aware Neural Rewards for Coherent Text Generation (Bosselut et al., NAACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/N18-1016.pdf