Co-evolution of language and agents in referential games

Gautier Dagan, Dieuwke Hupkes, Elia Bruni

Language Grounding to Vision, Robotics and Beyond Long paper Paper

Gather-3F: Apr 23, Gather-3F: Apr 23 (13:00-15:00 UTC) [Join Gather Meeting]

You can open the pre-recorded video in separate windows.

Abstract: Referential games offer a grounded learning environment for neural agents which accounts for the fact that language is functionally used to communicate. However, they do not take into account a second constraint considered to be fundamental for the shape of human language: that it must be learnable by new language learners. Cogswell et al. (2019) introduced cultural transmission within referential games through a changing population of agents to constrain the emerging language to be learnable. However, the resulting languages remain inherently biased by the agents’ underlying capabilities. In this work, we introduce Language Transmission Simulator to model both cultural and architectural evolution in a population of agents. As our core contribution, we empirically show that the optimal situation is to take into account also the learning biases of the language learners and thus let language and agents co-evolve. When we allow the agent population to evolve through architectural evolution, we achieve across the board improvements on all considered metrics and surpass the gains made with cultural transmission. These results stress the importance of studying the underlying agent architecture and pave the way to investigate the co-evolution of language and agent in language emergence studies.
NOTE: Video may display a random order of authors. Correct author list is at the top of this page.

Connected Papers in EACL2021

Similar Papers

Incremental Beam Manipulation for Natural Language Generation
James Hargreaves, Andreas Vlachos, Guy Emerson,
On the Computational Modelling of Michif Verbal Morphology
Fineen Davis, Eddie Antonio Santos, Heather Souter,
Attention Can Reflect Syntactic Structure (If You Let It)
Vinit Ravishankar, Artur Kulmizev, Mostafa Abdou, Anders Søgaard, Joakim Nivre,