Work

On the Spontaneous Emergence of Discrete and Compositional Signals

Year: 2020

Type: conference-paper

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.

Source: Proceedings of the conference - Association for Computational Linguistics. Meeting

DOI: 10.18653/v1/2020.acl-main.433

Authors: Nur Geffen Lan, Emmanuel Chemla, Shane Steinert-Threlkeld