mlsanityData to 7 Oct 2026

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

arXiv 2303.04544 ↗First posted 8 Mar 2023cs.AI cs.CL cs.MAcited by 2

Not on the map. Why?

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 32 of its 163 references that are in the map. First posted on arXiv 8 Mar 2023.

Builds on

32 of 163 references.

References · 32

  1. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  2. 2014Deep Visual-Semantic Alignments for Generating Image Descriptionscited by 966
  3. 2019Theoretical Limitations of Self-Attention in Neural Sequence Modelscited by 286
  4. 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 257
  5. 2020Experience Grounds Languagecited by 241
  6. 2019The Hanabi Challenge: A New Frontier for AI Researchcited by 194
  7. 2016Multi-Agent Cooperation and the Emergence of (Natural) Languagecited by 181
  8. 2020Emergent Multi-Agent Communication in the Deep Learning Eracited by 168
  9. 2020Compositionality and Generalization in Emergent Languagescited by 103
  10. 2018Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Inputcited by 102
  11. 2017Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialogcited by 86
  12. 2019Measuring Compositionality in Representation Learningcited by 84
20 more
  1. 2020Compositional Languages Emerge in a Neural Iterated Learning Modelcited by 75
  2. 2019Ease-of-Teaching and Language Structure from Emergent Communicationcited by 65
  3. 2020Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learningcited by 65
  4. 2017Image-Grounded Conversations: Multimodal Context for Natural Question and Response Generationcited by 59
  5. 2019Environmental drivers of systematicity and generalization in a situated agentcited by 50
  6. 2018How agents see things: On visual representations in an emergent language gamecited by 45
  7. 2021Emergent Communication of Generalizationscited by 41
  8. 2018Symbol Emergence in Cognitive Developmental Systems: a Surveycited by 39
  9. 2015Symbol Emergence in Robotics: A Surveycited by 31
  10. 2018Compositional Obverter Communication Learning From Raw Visual Inputcited by 30
  11. 2017Emergent Translation in Multi-Agent Communicationcited by 22
  12. 2018Emergence of Communication in an Interactive World with Consistent Speakerscited by 18
  13. 2019Emergence of Compositional Language with Deep Generational Transmissioncited by 17
  14. 2015The Spontaneous Emergence of Conventions: An Experimental Study of Cultural Evolutioncited by 16
  15. 2022Emergent Communication through Metropolis-Hastings Naming Game with Deep Generative Modelscited by 16
  16. 2021Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communicationcited by 12
  17. 2020Measuring non-trivial compositionality in emergent communicationcited by 10
  18. 2020On the Spontaneous Emergence of Discrete and Compositional Signalscited by 6
  19. 2021Mutual influence between language and perception in multi-agent communication gamescited by 5
  20. 2013Individual Biases, Cultural Evolution, and the Statistical Nature of Language Universals: The Case of Colour Naming Systemscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2024Bidirectional Emergent Language in Situated Environmentscited by 1
  2. 2026Building Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulationscited by 0