Articles and book chapters Articles and book chapters

Return to Full Page

Anti-efficient encoding in emergent communication

  • Authors
  • Chaabouni, R.; Kharitonov, E.; Dupoux, E.; Baroni, M.
  • UPF authors
  • Authors of the book
  • apos;Alché-Buc, F.; Fox, E.; Garnett, R. (eds.)
  • Book title
  • Advances in Neural Information Processing Systems 32 (NIPS 2019)
  • Publisher
  • Curran Associates
  • Publication year
  • 2019
  • Pages
  • 6290-6300
  • Abstract
  • apos;, are trained to play a signaling game. Surprisingly, we find that networks develop an \emph{anti-efficient} encoding scheme, in which the most frequent inputs are associated to the longest messages, and messages in general are skewed towards the maximum length threshold. This anti-efficient code appears easier to discriminate for the listener, and, unlike in human communication, the speaker does not impose a contrasting least-effort pressure towards brevity. Indeed, when the cost function includes a penalty for longer messages, the resulting message distribution starts respecting ZLA. Our analysis stresses the importance of studying the basic features of emergent communication in a highly controlled setup, to ensure the latter will not strand too far from human language. Moreover, we present a concrete illustration of how different functional pressures can lead to successful communication codes that lack basic properties of human language, thus highlighting the role such pressures play in the latter.
  • Complete citation
  • Chaabouni, R.; Kharitonov, E.; Dupoux, E.; Baroni, M.. Anti-efficient encoding in emergent communication. In: Wallach, H.; Larochelle, H.; Beygelzimer, A.; d'Alché-Buc, F.; Fox, E.; Garnett, R. (eds.). Advances in Neural Information Processing Systems 32 (NIPS 2019). 1 ed. Vancouver, BC: Curran Associates; 2019. p. 6290-6300.