Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication
Not on the map. Why?
Abstract (arXiv)
Effective communication requires the ability to refer to specific parts of an observation in relation to others. While emergent communication literature shows success in developing various language properties, no research has shown the emergence of such positional references. This paper demonstrates how agents can communicate about spatial relationships within their observations. The results indicate that agents can develop a language capable of expressing the relationships between parts of their observation, achieving over 90% accuracy when trained in a referential game which requires such communication. Using a collocation measure, we demonstrate how the agents create such references. This analysis suggests that agents use a mixture of non-compositional and compositional messages to convey spatial relationships. We also show that the emergent language is interpretable by humans. The translation accuracy is tested by communicating with the receiver agent, where the receiver achieves over 78% accuracy using parts of this lexicon, confirming that the interpretation of the emergent language was successful.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 15 of its 31 references that are in the map. First posted on arXiv 11 Jun 2024.
Builds on
15 of 31 references.
References · 15
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
- 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
- 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 263
- 2020Emergent Multi-Agent Communication in the Deep Learning Eracited by 170
- 2017Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbolscited by 125
- 2020Compositionality and Generalization in Emergent Languagescited by 103
- 2018Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Inputcited by 102
- 2019Anti-efficient encoding in emergent communicationcited by 59
- 2019EGG: a toolkit for research on Emergence of lanGuage in Gamescited by 42
- 2021Emergent Communication of Generalizationscited by 42
- 2021Interpretable agent communication from scratch (with a generic visual processor emerging on the side)cited by 25
- 2020"LazImpa": Lazy and Impatient neural agents learn to communicate efficientlycited by 23
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.
- 2025From Grunts to Lexicons: Emergent Language from Cooperative Foragingcited by 1
- 2025Morpheme Induction for Emergent Languagecited by 0
- 2026Emergent Language as an Approach to Conscious AIcited by 0
- 2026Emergent Language as an Approach to Conscious AI4 Jun 2026
- 2025Morpheme Induction for Emergent Language3 Oct 2025
- 2025From Grunts to Lexicons: Emergent Language from Cooperative Foraging19 May 2025