On the Spontaneous Emergence of Discrete and Compositional Signals
This work addresses the fundamental question of language emergence for researchers in AI and linguistics, but it is incremental as it builds on existing signaling game frameworks.
The authors tackled the problem of understanding how discrete and compositional signals emerge in language by proposing a framework using neural agents in signaling games with a continuous latent space, and found that discrete messages emerge naturally but are not compositional.
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.