On the Spontaneous Emergence of Discrete and Compositional Signals

2020/04/30 by Lan, Nur Geffen, Chemla, Emmanuel, Steinert-Threlkeld, Shane
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multiagent Systems (cs.MA)

paper · doi:10.48550/arxiv.2005.00110

Abstract

We propose a general framework to study language emergence through signaling games with neural agents. Using a continuous latent space, we are able to (i) train using backpropagation, (ii) show that discrete messages nonetheless naturally emerge. We explore whether categorical perception effects follow and show that the messages are not compositional.

Related

• Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input
• Emergence of Numeric Concepts in Multi-Agent Autonomous Communication
• Learning Compositional Negation in Populations of Roth-Erev and Neural Agents
• Compositional properties of emergent languages in deep learning
• The Emergence of Compositional Languages for Numeric Concepts Through Iterated Learning in Neural Agents