@InProceedings{yu-eshghi-lemon:2017:W17-55,
  author    = {Yu, Yanchao  and  Eshghi, Arash  and  Lemon, Oliver},
  title     = {VOILA: An Optimised Dialogue System for Interactively Learning Visually-Grounded Word Meanings (Demonstration System)},
  booktitle = {Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue},
  month     = {August},
  year      = {2017},
  address   = {Saarbrücken, Germany},
  publisher = {Association for Computational Linguistics},
  pages     = {197--200},
  abstract  = {We present VOILA: an optimised, multi- modal dialogue agent for interactive
	learning of visually grounded word meanings from a human user. VOILA is: (1)
	able to learn new visual categories interactively from users from scratch; (2)
	trained on real human-human dialogues in the same domain, and so is able to
	conduct natural spontaneous dialogue; (3) optimised to find the most effective
	trade-off between the accuracy of the visual categories it learns and the cost
	it incurs to users. VOILA is deployed on Furhat, a human-like, multi-modal
	robot head with back-projection of the face, and a graphical virtual character.},
  url       = {http://aclweb.org/anthology/W17-5524}
}