@InProceedings{bosselut-EtAl:2018:N18-1,
  author    = {Bosselut, Antoine  and  Celikyilmaz, Asli  and  He, Xiaodong  and  Gao, Jianfeng  and  Huang, Po-Sen  and  Choi, Yejin},
  title     = {Discourse-Aware Neural Rewards for Coherent Text Generation},
  booktitle = {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},
  publisher = {Association for Computational Linguistics},
  pages     = {173--184},
  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.},
  url       = {http://www.aclweb.org/anthology/N18-1016}
}