Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication

Olaf Lipinski, A. Sobey, Federico Cerutti, Timothy J. Norman
2/3/2026

No official code found. Best implementation: olipinski/TPG (1 star, MIT, last commit 2024-10-28).

Abstract

Effective communication requires the ability to refer to specific parts of an observation in relation to others. While emergent communication literature shows success in developing various language properties, no research has shown the emergence of such positional references. This paper demonstrates how agents can communicate about spatial relationships within their observations. The results indicate that agents can develop a language capable of expressing the relationships between parts of their observation, achieving over 90% accuracy when trained in a referential game which requires such communication. Using a collocation measure, we demonstrate how the agents create such references. This analysis suggests that agents use a mixture of non-compositional and compositional messages to convey spatial relationships. We also show that the emergent language is interpretable by humans. The translation accuracy is tested by communicating with the receiver agent, where the receiver achieves over 78% accuracy using parts of this lexicon, confirming that the interpretation of the emergent language was successful.

View on arXivView PDF

Code Implementations(1)

olipinski/TPGCommunity100%
MIT

Code accompanying our paper "Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication", presented at NeurIPS 2024.

10Python, Jupyter NotebookOct 28, 20241 years agoMIT

Similar Papers

Cite this paper

@article{lipinski2026speaking,
  title  = {Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication},
  author = {Olaf Lipinski and A. Sobey and Federico Cerutti and Timothy J. Norman},
  year   = {2026},
  eprint = {2406.07277},
  archivePrefix = {arXiv},
  doi    = {10.48550/arXiv.2406.07277},
  url    = {https://arxiv.org/abs/2406.07277},
  journal = {NEURIPS 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.07277.svg)](https://codeofpaper.com/paper/2406.07277)

Discussion