@InProceedings{casanueva-EtAl:2018:SIGdial,
  author    = {Casanueva, Iñigo  and  Budzianowski, Paweł  and  Ultes, Stefan  and  Kreyssig, Florian  and  Tseng, Bo-Hsiang  and  Wu, Yen-chen  and  Gasic, Milica},
  title     = {Feudal Dialogue Management with Jointly Learned Feature Extractors},
  booktitle = {Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue},
  month     = {July},
  year      = {2018},
  address   = {Melbourne, Australia},
  publisher = {Association for Computational Linguistics},
  pages     = {332--337},
  abstract  = {Reinforcement learning (RL) is a promising dialogue policy optimisation approach, but traditional RL algorithms fail to scale to large domains. Recently, Feudal Dialogue Management (FDM), has shown to increase the scalability to large domains by decomposing the dialogue management decision into two steps, making use of the domain ontology to abstract the dialogue state in each step. In order to abstract the state space, however, previous work on FDM relies on handcrafted feature functions. In this work, we show that these feature functions can be learned jointly with the policy model while obtaining similar performance, even outperforming the handcrafted features in several environments and domains.},
  url       = {http://www.aclweb.org/anthology/W18-5038}
}