Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication
Olaf Lipinski, Adam J. Sobey, Federico Cerutti, Timothy J. Norman
Abstract
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 64059a0a-832a-4425-842f-b9de417da8b2Cited by top-tier papers2
- Communicating in Emergent Language with an Induced Morphological PhrasebookBrendon Boldt, David R. MortensenACL 2026
- Morpheme Induction for Emergent LanguageBrendon Boldt, David R. MortensenEMNLP 2025
Builds on7
- Emergent Communication at ScaleRahma Chaabouni, Florian Strub, Florent Altché, Eugene Tarassov et al.ICLR 2022 · 65 citations
- Emergent Communication of GeneralizationsJesse Mu, Noah D. GoodmanNeurIPS 2021 · 60 citations
- Compositionality and Generalization In Emergent LanguagesRahma Chaabouni, Eugene Kharitonov, Diane Bouchacourt, Emmanuel Dupoux et al.ACL 2020 · 40 citations
- Interpretable agent communication from scratch (with a generic visual processor emerging on the side)Roberto Dessì, Eugene Kharitonov, Marco BaroniNeurIPS 2021 · 33 citations
- Emergent Communication with Conversational RepairMitja NikolausICLR 2024 · 4 citations
Related papers
- Learning Multi-Object Positional Relationships via Emergent CommunicationYicheng Feng, Boshi An, Zongqing LuAAAI 2024 · 4 citations
- The Emergence of Compositional Languages in Multi-entity Referential Games: from Image to Graph RepresentationsDaniel Akkerman, Phong Le, Raquel G. AlhamaEMNLP 2024 · 1 citation
- Emergent Communication for Numerical Concepts GeneralizationEnshuai Zhou, Yifan Hao, Rui Zhang, Yuxuan Guo et al.AAAI 2024 · 5 citations
- Incorporating Pragmatic Reasoning Communication into Emergent LanguageYipeng Kang, Tonghan Wang, Gerard de MeloNeurIPS 2020 · 26 citations
- Revisiting Populations in multi-agent CommunicationPaul Michel, Mathieu Rita, Kory Wallace Mathewson, Olivier Tieleman et al.ICLR 2023
