Unsupervised Translation of Emergent Communication

Ido Levy, Orr Paradise, Boaz Carmeli, Ron Meir, Shafi Goldwasser +1 more
2/11/2025
cs.CLcs.AI

No confident code implementation found for this paper.

Abstract

Emergent Communication (EC) provides a unique window into the language systems that emerge autonomously when agents are trained to jointly achieve shared goals. However, it is difficult to interpret EC and evaluate its relationship with natural languages (NL). This study employs unsupervised neural machine translation (UNMT) techniques to decipher ECs formed during referential games with varying task complexities, influenced by the semantic diversity of the environment. Our findings demonstrate UNMT's potential to translate EC, illustrating that task complexity characterized by semantic diversity enhances EC translatability, while higher task complexity with constrained semantic variability exhibits pragmatic EC, which, although challenging to interpret, remains suitable for translation. This research marks the first attempt, to our knowledge, to translate EC without the aid of parallel data.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

A Review of the Applications of Deep Learning-Based Emergent Communication

82% match2024

Learning and communication pressures in neural networks: Lessons from emergent communication

81% match2024

Automated Semantic Rules Detection (ASRD) for Emergent Communication Interpretation

80% match1 repo2026

Searching for the Most Human-like Emergent Language

80% match2025

Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication

80% match1 repo12026

AI Mother Tongue: Self-Emergent Communication in MARL via Endogenous Symbol Systems

79% match2025

Cite this paper

@article{levy2025unsupervised,
  title  = {Unsupervised Translation of Emergent Communication},
  author = {Ido Levy and Orr Paradise and Boaz Carmeli and Ron Meir and Shafi Goldwasser and Yonatan Belinkov},
  year   = {2025},
  eprint = {2502.07552},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2502.07552v1}
}

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/2502.07552.svg)](https://codeofpaper.com/paper/2502.07552)

Discussion