@InProceedings{li-EtAl:2017:EMNLP20175,
  author    = {Li, Jiwei  and  Monroe, Will  and  Shi, Tianlin  and  Jean, S\'ebastien  and  Ritter, Alan  and  Jurafsky, Dan},
  title     = {Adversarial Learning for Neural Dialogue Generation},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {2157--2169},
  abstract  = {We apply adversarial training to open-domain dialogue generation,
	training a system to produce sequences that are
	 indistinguishable from human-generated dialogue utterances. 
	We cast the task as a reinforcement learning problem where we jointly train two
	systems: a generative model to produce response sequences, and a
	discriminator---analagous to the human evaluator in the Turing test--- to
	distinguish between 
	 the 
	 human-generated dialogues and the machine-generated ones. 
	In this generative adversarial network approach,
	the outputs from the discriminator are 
	used to encourage the system towards more human-like dialogue.
	Further, we investigate models
	for adversarial  evaluation that 
	uses success in fooling an adversary as a dialogue evaluation metric,
	while avoiding a number of potential pitfalls.
	Experimental results on several
	metrics, including adversarial evaluation, demonstrate
	that the adversarially-trained system generates higher-quality responses
	than previous baselines},
  url       = {https://www.aclweb.org/anthology/D17-1230}
}