2018

How agents see things: On visual representations in an emergent language game

Bouchacourt, Diane, Baroni, Marco

Understand

There is growing interest in the language developed by agents interacting in emergent-communication settings.

  • Earlier studies have focused on the agents' symbol usage, rather than on their representation of visual input.
  • In this paper, we consider the referential games of Lazaridou et al.
  • (2017) and investigate the representations the agents develop during their evolving interaction.

Built on

  • Convention

    David Lewis. 1969 · 1969

    Earlier work this paper cites.

  • Simple statistical gradient-following algorithms for connectionist reinforcement learning

    Ronald Williams. 1992 · 1992

    Earlier work this paper cites.

  • Conceptual pacts and lexical choice in conversation

    Susan E. Brennan and Herbert H. Clark. 1996 · 1996

    Earlier work this paper cites.

  • Linguistic evolution through language acquisition

    Ted Briscoe, editor. 2002 · 2002

    Earlier work this paper cites.

  • Simulating the evolution of language

    Angelo Cangelosi and Domenico Parisi, editors. 2002 · 2002

    Earlier work this paper cites.

  • Representational similarity analysis: Connecting the branches of systems neuroscience

    Nikolaus Kriegeskorte, Marieke Mur, and Peter Bandettini. 2008 · 2008

    Earlier work this paper cites.

Similar

  • Imagenet: A large-scale hierarchical image database

    Jia Deng, Wei Dong, Richard Socher, Lia-Ji Li, and Li Fei-Fei. 2009 · 2009

    Cited alongside, same era.

  • What is the best multi-stage architecture for object recognition?

    Kevin Jarrett, Koray Kavukcuoglu, Marc’Aurelio Ranzato, and Yann LeCun. 2009 · 2009

    Cited alongside, same era.

  • Categorical perception

    Robert Goldstone and Andrew Hendrickson. 2010 · 2010

    Cited alongside, same era.

  • Signals: Evolution, learning, and information

    Brian Skyrms. 2010 · 2010

    Cited alongside, same era.

  • Experiments in Cultural Language Evolution

    Luc Steels, editor. 2012 · 2012

    Cited alongside, same era.

  • Visualizing and understanding convolutional networks

    Matthew Zeiler and Rob Fergus. 2014 · 2014

    Cited alongside, same era.

Then

  • Very deep convolutional networks for large-scale image recognition

    Karen Simonyan and Andrew Zisserman. 2015 · 2015

    Later among the works it cites.

  • Learning to play Guess Who? and inventing a grounded language as a consequence

    Emilio Jorge, Mikael Kågebäck, and Emil Gustavsson. 2016 · 2016

    Later among the works it cites.

  • Emergence of language with multi-agent games: Learning to communicate with sequences of symbols

    Serhii Havrylov and Ivan Titov. 2017 · 2017

    Later among the works it cites.

  • Multi-agent cooperation and the emergence of (natural) language

    Angeliki Lazaridou, Alexander Peysakhovich, and Marco Baroni. 2017 · 2017

    Later among the works it cites.

  • Emergent communication in a multi-modal, multi-step referential game

    Katrina Evtimova, Andrew Drozdov, Douwe Kiela, and Kyunghyun Cho. 2018 · 2018

    Closest in time.

  • Emergent translation in multi-agent communication

    Jason Lee, Kyunghyun Cho, Jason Weston, and Douwe Kiela. 2018 · 2018

    Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…