Towards Multi-Agent Communication-Based Language Learning

@article{Lazaridou2016TowardsMC,
  title={Towards Multi-Agent Communication-Based Language Learning},
  author={Angeliki Lazaridou and Nghia The Pham and Marco Baroni},
  journal={CoRR},
  year={2016},
  volume={abs/1605.07133}
}
We propose an interactive multimodal framework for language learning. Instead of being passively exposed to large amounts of natural text, our learners (implemented as feed-forward neural networks) engage in cooperative referential games starting from a tabula rasa setup, and thus develop their own language from the need to communicate in order to succeed at the game. Preliminary experiments provide promising results, but also suggest that it is important to ensure that agents trained in this… CONTINUE READING
Tweets
This paper has been referenced on Twitter 21 times. VIEW TWEETS

From This Paper

Figures, tables, and topics from this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 32 REFERENCES

Dialog - based language learning

  • Ronald J Williams
  • 2016

Trevor Darrell

  • Jacob Andreas, Marcus Rohrbach
  • and Dan Klein.
  • 2016

tering the game of go with deep neural networks and tree search

  • Andrew Zisserman
  • Nature
  • 2016

A roadmap towards machine intelligence

  • Margaret Mitchell, Kees van Deemter, Ehud Reiter
  • 2015

Armand Joulin

  • Tomas Mikolov
  • and Marco Baroni.
  • 2015

Similar Papers

Loading similar papers…