# Semantic Communication with Conceptual Spaces

arXiv: https://arxiv.org/abs/2210.01629 · HTML: https://mlsanity.com/paper/2210.01629/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2022.

## Built on by (most cited first, 1 of 1)

- [Autoencoder-Based Domain Learning for Semantic Communication with Conceptual Spaces](https://mlsanity.com/paper/2401.16569/) (2024)

## Abstract (arXiv)

Despite the fact that Shannon and Weaver's Mathematical Theory of Communication was published over 70 years ago, all communication systems continue to operate at the first of three levels defined in this theory: the technical level. In this letter, we argue that a transition to the semantic level embodies a natural, important step in the evolution of communication technologies. Furthermore, we propose a novel approach to engineering semantic communication using conceptual spaces and functional compression. We introduce a model of semantic communication utilizing this approach, and simulate communication of image semantics demonstrating a 99.79% reduction in rate.