Articles and book chapters Articles and book chapters

Return to Full Page

Focus on what's informative and ignore what's not: Communication strategies in a referential game

  • Authors
  • Dessi, R.; Bouchacourt, D.; Crepaldi, D.; Baroni, M.
  • UPF authors
  • BARONI ., MARCO;
  • Authors of the book
  • -
  • Book title
  • 3d NeurIPS Workshop on Emergent Communication
  • Publication year
  • 2019
  • Pages
  • -
  • Abstract
  • Research in multi-agent cooperation has shown that artificial agents are able to learn to play a simple referential game while developing a shared lexicon. This lexicon is not easy to analyze, as it does not show many properties of a natural language. In a simple referential game with two neural network-based agents, we analyze the object-symbol mapping trying to understand what kind of strategy was used to develop the emergent language. We see that, when the environment is uniformly distributed, the agents rely on a random subset of features to describe the objects. When we modify the objects making one feature non-uniformly distributed,the agents realize it is less informative and start to ignore it, and, surprisingly, they make a better use of the remaining features. This interesting result suggests that more natural, less uniformly distributed environments might aid in spurring the emergence of better-behaved languages.
  • Complete citation
  • Dessi, R.; Bouchacourt, D.; Crepaldi, D.; Baroni, M.. Focus on what's informative and ignore what's not: Communication strategies in a referential game. In: -. 3d NeurIPS Workshop on Emergent Communication. 1 ed. 2019.