Interpreting Decision-Making in Interactive Visual Dialogue

@inproceedings{Sharma2018InterpretingDI,
  title={Interpreting Decision-Making in Interactive Visual Dialogue},
  author={Urvashi Sharma},
  year={2018}
}
Dialogue systems that involve long-term planning can strongly benefit from a high-level notion of dialogue strategy and can avoid making poor decisions early in the game and opt for broadly successful strategies instead. A strategy-signal can additionally be used as a conditioning input on the dialogue generation mechanism allowing better training and generalization over a vastly smaller generation space. In this work, we first analyze the human game-play strategy, using regular expression… CONTINUE READING

Similar Papers

References

Publications referenced by this paper.
SHOWING 1-10 OF 44 REFERENCES

Deep Residual Learning for Image Recognition

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Long Short-Term Memory

  • Neural Computation
  • 1997
VIEW 15 EXCERPTS
HIGHLY INFLUENTIAL

GuessWhat?! Visual Object Discovery through Multi-modal Dialogue

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Auto-Encoding Variational Bayes

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Deep Learning

VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL

Generating Sentences from a Continuous Space

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL