@InProceedings{chang-EtAl:2017:EMNLP2017,
  author    = {Chang, Cheng  and  Yang, Runzhe  and  Chen, Lu  and  Zhou, Xiang  and  Yu, Kai},
  title     = {Affordable On-line Dialogue Policy Learning},
  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     = {2200--2209},
  abstract  = {The key to building an evolvable dialogue system in real-world scenarios is to
	ensure an affordable on-line dialogue policy learning, which requires the
	on-line learning process to be safe, efficient and economical. But in reality,
	due to the scarcity of real interaction data, the dialogue system usually grows
	slowly. Besides, the poor initial dialogue policy easily leads to bad user
	experience and incurs a failure of attracting users to contribute training
	data, so that the learning process is unsustainable. To accurately depict this,
	 two quantitative metrics are proposed to assess safety and efficiency issues.
	For solving the unsustainable learning problem, we proposed a complete
	companion teaching framework incorporating the guidance from the human teacher.
	Since the human teaching is expensive, we compared various teaching schemes
	answering the question how and when to teach, to economically utilize teaching
	budget, so that make the online learning process affordable.},
  url       = {https://www.aclweb.org/anthology/D17-1234}
}