# Emergent Language Generalization and Acquisition Speed are not tied to Compositionality

arXiv: https://arxiv.org/abs/2004.03420 · HTML: https://mlsanity.com/paper/2004.03420/

## Key facts

- Cited by 17 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 7 Apr 2020.

## Built on by (most cited first, 17 of 17)

- [Emergent Communication: Generalization and Overfitting in Lewis Games](https://mlsanity.com/paper/2209.15342/) (2022)
- [Linking Emergent and Natural Languages via Corpus Transfer](https://mlsanity.com/paper/2203.13344/) (2022)
- [Iterated Learning Improves Compositionality in Large Vision-Language Models](https://mlsanity.com/paper/2404.02145/) (2024)
- [A Review of the Applications of Deep Learning-Based Emergent Communication](https://mlsanity.com/paper/2407.03302/) (2024)
- [On The Specialization of Neural Modules](https://mlsanity.com/paper/2409.14981/) (2024)
- [Towards More Human-like AI Communication: A Review of Emergent Communication Research](https://mlsanity.com/paper/2308.02541/) (2023)
- [Emergent Language: A Survey and Taxonomy](https://mlsanity.com/paper/2409.02645/) (2024)
- [The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMs](https://mlsanity.com/paper/2602.11583/) (2026)
- [Defending Compositionality in Emergent Languages](https://mlsanity.com/paper/2206.04751/) (2022)
- [Neural networks can understand compositional functions that humans do not, in the context of emergent communication](https://mlsanity.com/paper/2103.04180/) (2021)
- [Recommendations for Systematic Research on Emergent Language](https://mlsanity.com/paper/2206.11302/) (2022)
- [A framework for the emergence and analysis of language in social learning agents](https://mlsanity.com/paper/2305.02632/) (2023)
- [Context-dependent communication under environmental constraints](https://mlsanity.com/paper/2305.05821/) (2023)
- [ELCC: the Emergent Language Corpus Collection](https://mlsanity.com/paper/2407.04158/) (2024)
- [On the Correspondence between Compositionality and Imitation in Emergent Neural Communication](https://mlsanity.com/paper/2305.12941/) (2023)
- [Emergent Compositional Communication for Latent World Properties](https://mlsanity.com/paper/2604.03266/) (2026)
- [Morpheme Induction for Emergent Language](https://mlsanity.com/paper/2510.03439/) (2025)

## Abstract (arXiv)

Studies of discrete languages emerging when neural agents communicate to solve a joint task often look for evidence of compositional structure. This stems for the expectation that such a structure would allow languages to be acquired faster by the agents and enable them to generalize better. We argue that these beneficial properties are only loosely connected to compositionality. In two experiments, we demonstrate that, depending on the task, non-compositional languages might show equal, or better, generalization performance and acquisition speed than compositional ones. Further research in the area should be clearer about what benefits are expected from compositionality, and how the latter would lead to them.