@InProceedings{yu-eshghi-lemon:2017:RoboNLP,
  author    = {Yu, Yanchao  and  Eshghi, Arash  and  Lemon, Oliver},
  title     = {Learning how to Learn: An Adaptive Dialogue Agent for Incrementally Learning Visually Grounded Word Meanings},
  booktitle = {Proceedings of the First Workshop on Language Grounding for Robotics},
  month     = {August},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {10--19},
  abstract  = {We present an optimised multi-modal dialogue agent for interactive learning of
	visually grounded word meanings from a human tutor, trained on real human-human
	tutoring data. Within a life-long interactive learning period, the agent,
	trained using Reinforcement Learning (RL), must be able to handle natural
	conversations with human users, and achieve  good learning performance (i.e.
	accuracy) while minimising human effort in the learning process. We train and
	evaluate this  system in interaction with a simulated human tutor, which is
	built on the BURCHAK corpus -- a Human-Human Dialogue dataset for the visual
	learning task. The results show that: 1) The learned policy can coherently
	interact with the simulated user to achieve the goal of the task (i.e. learning
	visual attributes of  objects, e.g. colour and shape); and 2) it finds a better
	trade-off between  classifier accuracy and tutoring costs than hand-crafted
	rule-based policies, including ones with dynamic policies.},
  url       = {http://www.aclweb.org/anthology/W17-2802}
}