# Models of symbol emergence in communication: a conceptual review and a guide for avoiding local minima

arXiv: https://arxiv.org/abs/2303.04544 · HTML: https://mlsanity.com/paper/2303.04544/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 163 references that are in the map.
- First posted on arXiv 8 Mar 2023.

## Builds on (most cited first, 30 of 32)

- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [Theoretical Limitations of Self-Attention in Neural Sequence Models](https://mlsanity.com/paper/1906.06755/) (2019)
- [Emergence of Grounded Compositional Language in Multi-Agent Populations](https://mlsanity.com/paper/1703.04908/) (2017)
- [Experience Grounds Language](https://mlsanity.com/paper/2004.10151/) (2020)
- [The Hanabi Challenge: A New Frontier for AI Research](https://mlsanity.com/paper/1902.00506/) (2019)
- [Multi-Agent Cooperation and the Emergence of (Natural) Language](https://mlsanity.com/paper/1612.07182/) (2016)
- [Emergent Multi-Agent Communication in the Deep Learning Era](https://mlsanity.com/paper/2006.02419/) (2020)
- [Compositionality and Generalization in Emergent Languages](https://mlsanity.com/paper/2004.09124/) (2020)
- [Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input](https://mlsanity.com/paper/1804.03984/) (2018)
- [Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog](https://mlsanity.com/paper/1706.08502/) (2017)
- [Measuring Compositionality in Representation Learning](https://mlsanity.com/paper/1902.07181/) (2019)
- [Compositional Languages Emerge in a Neural Iterated Learning Model](https://mlsanity.com/paper/2002.01365/) (2020)
- [Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning](https://mlsanity.com/paper/2005.07064/) (2020)
- [Ease-of-Teaching and Language Structure from Emergent Communication](https://mlsanity.com/paper/1906.02403/) (2019)
- [Image-Grounded Conversations: Multimodal Context for Natural Question and Response Generation](https://mlsanity.com/paper/1701.08251/) (2017)
- [Environmental drivers of systematicity and generalization in a situated agent](https://mlsanity.com/paper/1910.00571/) (2019)
- [How agents see things: On visual representations in an emergent language game](https://mlsanity.com/paper/1808.10696/) (2018)
- [Emergent Communication of Generalizations](https://mlsanity.com/paper/2106.02668/) (2021)
- [Symbol Emergence in Cognitive Developmental Systems: a Survey](https://mlsanity.com/paper/1801.08829/) (2018)
- [Symbol Emergence in Robotics: A Survey](https://mlsanity.com/paper/1509.08973/) (2015)
- [Compositional Obverter Communication Learning From Raw Visual Input](https://mlsanity.com/paper/1804.02341/) (2018)
- [Emergent Translation in Multi-Agent Communication](https://mlsanity.com/paper/1710.06922/) (2017)
- [Emergence of Communication in an Interactive World with Consistent Speakers](https://mlsanity.com/paper/1809.00549/) (2018)
- [The Spontaneous Emergence of Conventions: An Experimental Study of Cultural Evolution](https://mlsanity.com/paper/1502.06910/) (2015)
- [Emergence of Compositional Language with Deep Generational Transmission](https://mlsanity.com/paper/1904.09067/) (2019)
- [Emergent Communication through Metropolis-Hastings Naming Game with Deep Generative Models](https://mlsanity.com/paper/2205.12392/) (2022)
- [Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication](https://mlsanity.com/paper/2111.06464/) (2021)
- [Measuring non-trivial compositionality in emergent communication](https://mlsanity.com/paper/2010.15058/) (2020)
- [On the Spontaneous Emergence of Discrete and Compositional Signals](https://mlsanity.com/paper/2005.00110/) (2020)

## Built on by (most cited first, 2 of 2)

- [Bidirectional Emergent Language in Situated Environments](https://mlsanity.com/paper/2408.14649/) (2024)
- [Building Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulations](https://mlsanity.com/paper/2609.26927/) (2026)

## Abstract (arXiv)

Computational simulations are a popular method for testing hypotheses about the emergence of communication. This kind of research is performed in a variety of traditions including language evolution, developmental psychology, cognitive science, machine learning, robotics, etc. The motivations for the models are different, but the operationalizations and methods used are often similar. We identify the assumptions and explanatory targets of several most representative models and summarise the known results. We claim that some of the assumptions -- such as portraying meaning in terms of mapping, focusing on the descriptive function of communication, modelling signals with amodal tokens -- may hinder the success of modelling. Relaxing these assumptions and foregrounding the interactions of embodied and situated agents allows one to systematise the multiplicity of pressures under which symbolic systems evolve. In line with this perspective, we sketch the road towards modelling the emergence of meaningful symbolic communication, where symbols are simultaneously grounded in action and perception and form an abstract system.