mlsanityData to 7 Oct 2026

Defending Compositionality in Emergent Languages

arXiv 2206.04751 ↗First posted 9 Jun 2022cs.CLcited by 8

Not on the map. Why?

Abstract (arXiv)

Compositionality has traditionally been understood as a major factor in productivity of language and, more broadly, human cognition. Yet, recently, some research started to question its status, showing that artificial neural networks are good at generalization even without noticeable compositional behavior. We argue that some of these conclusions are too strong and/or incomplete. In the context of a two-agent communication game, we show that compositionality indeed seems essential for successful generalization when the evaluation is done on a proper dataset.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 13 of its 23 references that are in the map. First posted on arXiv 9 Jun 2022.

Builds on

13 of 23 references.

References · 13

  1. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  2. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
  3. 2018Colorless green recurrent networks dream hierarchicallycited by 210
  4. 2019Good-Enough Compositional Data Augmentationcited by 158
  5. 2020Compositionality and Generalization in Emergent Languagescited by 103
  6. 2017Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialogcited by 86
  7. 2019Measuring Compositionality in Representation Learningcited by 84
  8. 2019Ease-of-Teaching and Language Structure from Emergent Communicationcited by 65
  9. 2019Linguistic generalization and compositionality in modern artificial neural networkscited by 58
  10. 2018Rearranging the Familiar: Testing Compositional Generalization in Recurrent Networkscited by 51
  11. 2019EGG: a toolkit for research on Emergence of lanGuage in Gamescited by 42
  12. 2019CNNs found to jump around more skillfully than RNNs: Compositional generalization in seq2seq convolutional networkscited by 22
1 more
  1. 2020Emergent Language Generalization and Acquisition Speed are not tied to Compositionalitycited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 4; 2025: 1; 2026: 1.

8 papers.

  1. 2024A Review of the Applications of Deep Learning-Based Emergent Communicationcited by 17
  2. 2024Emergent Language: A Survey and Taxonomycited by 12
  3. 2026The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMscited by 10
  4. 2024The Curious Case of Representational Alignment: Unravelling Visio-Linguistic Tasks in Emergent Communicationcited by 7
  5. 2024Semantics and Spatiality of Emergent Communicationcited by 2
  6. 2023On the Correspondence between Compositionality and Imitation in Emergent Neural Communicationcited by 1
  7. 2025A Compressive-Expressive Communication Framework for Compositional Representationscited by 1
  8. 2023Emergent Communication for Rules Reasoningcited by 0