mlsanityData to 7 Oct 2026

Unsupervised Translation of Emergent Communication

arXiv 2502.07552 ↗First posted 11 Feb 2025cs.CL cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 35 of its 58 references that are in the map. First posted on arXiv 11 Feb 2025.

Builds on

35 of 58 references.

References · 35

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  4. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  5. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  6. 2017Word Translation Without Parallel Datacited by 480
  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. 2018A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddingscited by 145
  10. 2018Phrase-Based & Neural Unsupervised Machine Translationcited by 138
  11. 2018Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Inputcited by 102
  12. 2017Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialogcited by 86
23 more
  1. 2019Measuring Compositionality in Representation Learningcited by 84
  2. 2018COCO-CN for Cross-Lingual Image Tagging, Captioning and Retrievalcited by 80
  3. 2019EGG: a toolkit for research on Emergence of lanGuage in Gamescited by 42
  4. 2022Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Languagecited by 42
  5. 2021Emergent Communication of Generalizationscited by 41
  6. 2020When Does Unsupervised Machine Translation Work?cited by 38
  7. 2018Compositional Obverter Communication Learning From Raw Visual Inputcited by 30
  8. 2019The Emergence of Compositional Languages for Numeric Concepts Through Iterated Learning in Neural Agentscited by 26
  9. 2017Emergent Translation in Multi-Agent Communicationcited by 22
  10. 2021Iterated learning for emergent systematicity in VQAcited by 21
  11. 2022Linking Emergent and Natural Languages via Corpus Transfercited by 19
  12. 2024How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teacherscited by 18
  13. 2024A Review of the Applications of Deep Learning-Based Emergent Communicationcited by 17
  14. 2017Translating Neuralesecited by 16
  15. 2018Unsupervised Cross-lingual Transfer of Word Embedding Spacescited by 16
  16. 2018Unsupervised Neural Machine Translation with Weight Sharingcited by 15
  17. 2023Towards More Human-like AI Communication: A Review of Emergent Communication Researchcited by 12
  18. 2021Expressivity of Emergent Language is a Trade-off between Contextual Complexity and Unpredictabilitycited by 11
  19. 2020ReferentialGym: A Nomenclature and Framework for Language Emergence & Grounding in (Visual) Referential Gamescited by 10
  20. 2023string2string: A Modern Python Library for String-to-String Algorithmscited by 9
  21. 2024Concept-Best-Matching: Evaluating Compositionality in Emergent Communicationcited by 7
  22. 2022A Theory of Unsupervised Translation Motivated by Understanding Animal Communicationcited by 6
  23. 2022Learning to translate by learning to communicatecited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Verifiable Semantics for Agent-to-Agent Communicationcited by 2
  2. 2026Portable Semantics, Private Dialects: Reuse and Negative Transfer in Latent Communication Between Language-Model Cellscited by 1
  3. 2026EmCom-Diffusion: Probing Visual Reflection in Emergent Languages via Image Generationcited by 0