# On the Spontaneous Emergence of Discrete and Compositional Signals

arXiv: https://arxiv.org/abs/2005.00110 · HTML: https://mlsanity.com/paper/2005.00110/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2020.

## Built on by (most cited first, 6 of 6)

- [Interpretable agent communication from scratch (with a generic visual processor emerging on the side)](https://mlsanity.com/paper/2106.04258/) (2021)
- [A Review of the Applications of Deep Learning-Based Emergent Communication](https://mlsanity.com/paper/2407.03302/) (2024)
- [Learning to translate by learning to communicate](https://mlsanity.com/paper/2207.07025/) (2022)
- [Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel](https://mlsanity.com/paper/2111.02827/) (2021)
- [Models of symbol emergence in communication: a conceptual review and a guide for avoiding local minima](https://mlsanity.com/paper/2303.04544/) (2023)
- [ELCC: the Emergent Language Corpus Collection](https://mlsanity.com/paper/2407.04158/) (2024)

## Abstract (arXiv)

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.