English

Emergent Linguistic Phenomena in Multi-Agent Communication Games

Computation and Language 2020-03-03 v2 Artificial Intelligence Social and Information Networks

Abstract

In this work, we propose a computational framework in which agents equipped with communication capabilities simultaneously play a series of referential games, where agents are trained using deep reinforcement learning. We demonstrate that the framework mirrors linguistic phenomena observed in natural language: i) the outcome of contact between communities is a function of inter- and intra-group connectivity; ii) linguistic contact either converges to the majority protocol, or in balanced cases leads to novel creole languages of lower complexity; and iii) a linguistic continuum emerges where neighboring languages are more mutually intelligible than farther removed languages. We conclude that intricate properties of language evolution need not depend on complex evolved linguistic capabilities, but can emerge from simple social exchanges between perceptually-enabled agents playing communication games.

Keywords

Cite

@article{arxiv.1901.08706,
  title  = {Emergent Linguistic Phenomena in Multi-Agent Communication Games},
  author = {Laura Graesser and Kyunghyun Cho and Douwe Kiela},
  journal= {arXiv preprint arXiv:1901.08706},
  year   = {2020}
}

Comments

EMNLP 2019

R2 v1 2026-06-23T07:21:49.904Z