Cover not available

Article published In: Interaction Studies
Vol. 22:2 (2021) ► pp.212–243

Get fulltext from our e-platform
JBE logo with link
PDF logo with download linkDownload PDF

Interaction history as a source of compositionality in emergent communication

 | University of Sussex | University of Warsaw
 | University of Warsaw
 | Polish Academy of Sciences
 | Polish Academy of Sciences | University of Oxford
 | University of Warsaw
Open Access logo
Available under the Creative Commons Attribution (CC BY) 4.0 license.

For any use beyond this license, please contact the publisher at rights@benjamins.nl.

Published online: 28 February 2022
DOI logo with link
https://doi.org/10.1075/is.21020.kor
Abstract
In this paper, we explore interaction history as a particular source of pressure for achieving emergent compositional communication in multi-agent systems. We propose a training regime implementing template transfer, the idea of carrying over learned biases across contexts. In the presented method, a sender-receiver dyad is first trained with a disentangled pair of objectives, and then the receiver is transferred to train a new sender with a standard objective. Unlike other methods (e.g. the obverter algorithm), the template transfer approach does not require imposing inductive biases on the architecture of the agents. We experimentally show the emergence of compositional communication using topographical similarity, zero-shot generalization and context-independence as evaluation metrics. The presented approach is connected to an important line of work in semiotics and developmental psycholinguistics: it supports a conjecture that compositional communication is scaffolded on simpler communication protocols.
Article outline
  • 1.Introduction
  • 2.Related work
    • Inductive biases for compositional communication
    • Obverter approach
    • Population-based training
    • Multi-task training
    • Evolutionary origins of grammar
    • Generalized signaling games
    • Motivation for our approach
  • 3.Method
    • 3.1Experimental setup
      • 3.1.1Dataset
      • 3.1.2Object naming game
    • 3.2Architecture of the agents
      • General setup
      • Vision module
      • Sender
      • Receiver
      • Hyperparameters
    • 3.3Template transfer approach
  • 4.Experiments and results
    • 4.1Measuring compositionality
      • Test set accuracy
      • Context-independence
      • Topographical similarity
    • 4.2Baselines
      • Random baseline
      • Same architecture
      • Obverter baseline
    • 4.3Results
    • 4.4Visualizing the activations of the receiver
  • 5.Discussion
    • Sources of compositionality
    • Evolutionary game-theoretic interpretation
    • Semiotic interpretation
    • Cognitive interpretation
    • Developmental interpretation
  • 6.Conclusions
    • Limitations
  • Acknowledgements
  • Notes
  • References
References (58)
References
Barrett, J., Skyrms, B., and Cochran, C. (2018). Hierarchical Models for the Evolution of Compositional Language. Institute for Mathematical Behavioral Sciences Technical Report MBS 18-03.Google Scholar logo with link to Google Scholar
Barrett, J. A. and Skyrms, B. (2017). Self-assembling Games. The British Journal for the Philosophy of Science, 68(2):329–353. Google Scholar logo with link to Google Scholar
Barrett, J. A., Skyrms, B., and Mohseni, A. (2019). Self-Assembling Networks. The British Journal for the Philosophy of Science, 70(1):301–325. Google Scholar logo with link to Google Scholar
Batali, J. (1998). Computational simulations of the emergence of grammar. Approach to the Evolution of Language, pages 405–426.Google Scholar logo with link to Google Scholar
Bogin, B., Geva, M., and Berant, J. (2018). Emergence of Communication in an Interactive World with Consistent Speakers. arXiv:1809.00549 [cs]. arXiv: 1809.00549.Google Scholar logo with link to Google Scholar
Bouchacourt, D. and Baroni, M. (2018). How agents see things: On visual representations in an emergent language game. arXiv:1808.10696 [cs]. arXiv: 1808.10696. Google Scholar logo with link to Google Scholar
Brighton, H. (2002). Compositional Syntax From Cultural Transmission. Artificial Life, 8(1):25–54. Google Scholar logo with link to Google Scholar
Brighton, H. and Kirby, S. (2006). Understanding Linguistic Evolution by Visualizing the Emergence of Topographic Mappings. Artificial Life, 12(2):229–242. Google Scholar logo with link to Google Scholar
Brown, P. F., Della-Pietra, S. A., Della-Pietra, V. J., and Mercer, R. L. (1993). The mathematics of statistical machine translation. Computational Linguistics, 19(2):263–313.Google Scholar logo with link to Google Scholar
Bruner, J. S. (1981). Intention in the structure of action and interaction. Advances in Infancy Research, 11:41–56.Google Scholar logo with link to Google Scholar
(1983). Child’s talk: learning to use language. W.W. Norton, New York, 1st ed edition.Google Scholar logo with link to Google Scholar
Cangelosi, A. (2001). Evolution of communication and language using signals, symbols, and words. IEEE Transactions on Evolutionary Computation, 5(2):93–101. Google Scholar logo with link to Google Scholar
Chaabouni, R., Kharitonov, E., Bouchacourt, D., Dupoux, E., and Baroni, M. (2020). Compositionality and Generalization In Emergent Languages. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4427–4442, Online. Association for Computational Linguistics. Google Scholar logo with link to Google Scholar
Choi, E., Lazaridou, A., and de Freitas, N. (2018). Compositional Obverter Communication Learning From Raw Visual Input. ICLR 2018. arXiv: 1804.02341.Google Scholar logo with link to Google Scholar
Cogswell, M., Lu, J., Lee, S., Parikh, D., and Batra, D. (2019). Emergence of Compositional Language with Deep Generational Transmission. ArXiv, abs/1904.09067.Google Scholar logo with link to Google Scholar
Cowley, S. J., editor (2011). Distributed language. Number v. 34 in Benjamins current topics. John Benjamins Pub. Co, Amsterdam; Philadelphia. OCLC: ocn741355729. Google Scholar logo with link to Google Scholar
Das, A., Kottur, S., Moura, J. M. F., Lee, S., and Batra, D. (2017). Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 20171. arXiv: 1703.06585. Google Scholar logo with link to Google Scholar
De Beule, J. and Bergen, B. K. (2006). On the emergence of compositionality. In The Evolution of Language, pages 35–42, Rome, Italy. World scientific. Google Scholar logo with link to Google Scholar
Deacon, T. W. (1998). The symbolic species: the co-evolution of language and the brain. Norton, New York, NY, norton paperback edition. OCLC: 254499872.Google Scholar logo with link to Google Scholar
Elman, J. L. (1990). Finding Structure in Time. Cognitive Science, 14(2):179–211. Google Scholar logo with link to Google Scholar
Foerster, J. N., Assael, Y. M., de Freitas, N., and Whiteson, S. (2016). Learning to Communicate with Deep Multi-Agent Reinforcement Learning. NIPS’16 Proceedings of the 30th International Conference on Neural Information Processing Systems. arXiv: 1605.06676.Google Scholar logo with link to Google Scholar
Gong, T., Shuai, L., and Zhang, M. (2014). Modelling language evolution: Examples and predictions. Physics of Life Reviews, 11(2):280–302. Google Scholar logo with link to Google Scholar
Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep learning. Adaptive computation and machine learning. The MIT Press, Cambridge, Massachusetts.Google Scholar logo with link to Google Scholar
Grouchy, P., D’Eleuterio, G. M. T., Christiansen, M. H., and Lipson, H. (2016). On The Evolutionary Origin of Symbolic Communication. Scientific Reports, 6:34615. Google Scholar logo with link to Google Scholar
Jaques, N., Lazaridou, A., Hughes, E., Gulcehre, C., Ortega, P. A., Strouse, D. J., Leibo, J. Z., and de Freitas, N. (2018). Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning. arXiv:1810.08647 [cs, stat]. arXiv: 1810.08647.Google Scholar logo with link to Google Scholar
Kharitonov, E. and Baroni, M. (2020). Emergent Language Generalization and Acquisition Speed are not tied to Compositionality. arXiv:2004.03420 [cs]. arXiv: 2004.03420. Google Scholar logo with link to Google Scholar
Kharitonov, E., Chaabouni, R., Bouchacourt, D., and Baroni, M. (2019). EGG: a toolkit for research on Emergence of lanGuage in Games. arXiv:1907.00852 [cs]. arXiv: 1907.00852. Google Scholar logo with link to Google Scholar
Kingma, D. P. and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv:1412.6980 [cs]. arXiv: 1412.6980.Google Scholar logo with link to Google Scholar
Kirby, S. (2001). Spontaneous evolution of linguistic structure-an iterated learning model of the emergence of regularity and irregularity. IEEE Transactions on Evolutionary Computation, 5(2):102–110. Google Scholar logo with link to Google Scholar
Kirby, S., Cornish, H., and Smith, K. (2008). Cumulative cultural evolution in the laboratory: An experimental approach to the origins of structure in human language. Proceedings of the National Academy of Sciences, 105(31):10681–10686. Google Scholar logo with link to Google Scholar
Korbak, T., Zubek, J., and Raczaszek-Leonardi, J. (2020). Measuring non-trivial compositionality in emergent communication. arXiv preprint arXiv:2010.15058.Google Scholar logo with link to Google Scholar
Kottur, S., Moura, J. M. F., Lee, S., and Batra, D. (2017). Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog. arXiv:1706.08502 [cs]. arXiv: 1706.08502. Google Scholar logo with link to Google Scholar
Kriegeskorte, N. (2008). Representational similarity analysis – connecting the branches of systems neuroscience. Frontiers in Systems Neuroscience. Google Scholar logo with link to Google Scholar
Kuciński, L., Korbak, T., Kolodziej, P., and Miloś, P. (2021). Catalytic role of noise and necessity of inductive biases in the emergence of compositional communication. In Advances in Neural Information Processing Systems.Google Scholar logo with link to Google Scholar
Lake, B. M., Ullman, T. D., Tenenbaum, J. B., and Gershman, S. J. (2016). Building Machines That Learn and Think Like People. arXiv:1604.00289 [cs, stat]. arXiv: 1604.00289.Google Scholar logo with link to Google Scholar
Lazaridou, A., Hermann, K. M., Tuyls, K., and Clark, S. (2018). Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input. arXiv:1804.03984 [cs]. arXiv: 1804.03984.Google Scholar logo with link to Google Scholar
Lazaridou, A., Peysakhovich, A., and Baroni, M. (2016). Multi-Agent Cooperation and the Emergence of (Natural) Language. arXiv:1612.07182 [cs]. arXiv: 1612.07182.Google Scholar logo with link to Google Scholar
LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P. (1998). Gradient-based learning applied to document recognition. In PROCEEDINGS OF THE IEEE, pages 2278–2324. Google Scholar logo with link to Google Scholar
Levenshtein, V. I. (1966). Binary Codes Capable of Correcting Deletions, Insertions and Reversals. Soviet Physics Doklady, 101:707.Google Scholar logo with link to Google Scholar
Lewis, D. K. (1969). Convention: a philosophical study. Blackwell, Oxford, nachdr. edition. OCLC: 837747718.Google Scholar logo with link to Google Scholar
Li, F. and Bowling, M. (2019). Ease-of-Teaching and Language Structure from Emergent Communication. arXiv:1906.02403 [cs]. arXiv: 1906.02403.Google Scholar logo with link to Google Scholar
Lowe, R., Foerster, J., Boureau, Y.-L., Pineau, J., and Dauphin, Y. (2019). On the Pitfalls of Measuring Emergent Communication. arXiv:1903.05168 [cs, stat]. arXiv: 1903.05168.Google Scholar logo with link to Google Scholar
Nomikou, I., Koke, M., and Rohlfing, K. J. (2017). Verbs in Mothers’ Input to Six-Month-Olds: Synchrony between Presentation, Meaning, and Actions Is Related to Later Verb Acquisition. Brain Sciences, 7(12):52. Google Scholar logo with link to Google Scholar
Nowak, M. A. and Krakauer, D. C. (1999). The evolution of language. Proceedings of the National Academy of Sciences, 96(14):8028–8033. Publisher: National Academy of Sciences Section: Biological Sciences. Google Scholar logo with link to Google Scholar
Oliphant, M. and Batali, J. (1997). Learning and the Emergence of Coordinated Communication. Center for Research on Language Newsletter, 111.Google Scholar logo with link to Google Scholar
Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., and Lerer, A. (2017). Automatic differentiation in PyTorch.Google Scholar logo with link to Google Scholar
Peirce, C. S. (1998). Collected papers of Charles Sanders Peirce. Thoemmes Press, Bristol, England. OCLC: ocm39692049.Google Scholar logo with link to Google Scholar
Raczaszek-Leonardi, J. (2012). Language as a System of Replicable Constraints. In LAWS, LANGUAGE and LIFE, volume 71, pages 295–333. Springer Netherlands, Dordrecht. Google Scholar logo with link to Google Scholar
Raczaszek-Leonardi, J., Nomikou, I., Rohlfing, K. J., and Deacon, T. W. (2018). Language Development From an Ecological Perspective: Ecologically Valid Ways to Abstract Symbols. Ecological Psychology, 30(1):39–73. Google Scholar logo with link to Google Scholar
Rainey, H. J., Zuberbühler, K., and Slater, P. J. B. (2004). Hornbills can distinguish between primate alarm calls. Proceedings of the Royal Society of London. Series B: Biological Sciences, 271(1540):755–759. Google Scholar logo with link to Google Scholar
Rumelhart, D. E., Hinton, G. E., and Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088):533–536. Google Scholar logo with link to Google Scholar
Ryan, M. and Rand, S. (1993). Sexual selection and signal evolution: the ghost of biases past. Philosophical Transactions of the Royal Society of London. Series B: Biological Sciences, 340(1292):187–195. Google Scholar logo with link to Google Scholar
Skyrms, B. (2010). Signals: evolution, learning, & information. Oxford University Press, Oxford; New York. OCLC: ocn477256653. Google Scholar logo with link to Google Scholar
Steinert-Threlkeld, S. (2020). Towards the Emergence of Non-trivial Compositionaliy. Philosophy of Science. Google Scholar logo with link to Google Scholar
Stern, D. N. (1974). The Goal and Structure of Mother-Infant Play. Journal of the American Academy of Child Psychiatry, 13(3):402–421. Google Scholar logo with link to Google Scholar
Tomasello, M., Carpenter, M., Call, J., Behne, T., and Moll, H. (2005). Understanding and sharing intentions: The origins of cultural cognition. Behavioral and Brain Sciences, 28(5):675–691. Google Scholar logo with link to Google Scholar
Wittgenstein, L. (1953). Philosophical Investigations. Basil Blackwell, Oxford.Google Scholar logo with link to Google Scholar
Yamashita, Y. and Tani, J. (2008). Emergence of Functional Hierarchy in a Multiple Timescale Neural Network Model: A Humanoid Robot Experiment. PLoS Computational Biology, 4(11):e1000220. Google Scholar logo with link to Google Scholar
Cited by (4)

Cited by four other publications

Jodairi Pineh, Aiyoub
2024. Review of Meredith, Giles & Stommel (2022): Analysing Digital Interaction. Revista Española de Lingüística Aplicada/Spanish Journal of Applied Linguistics 37:2 ► pp. 769 ff. DOI logo
Zubek, Julian, Tomasz Korbak & Joanna Rączaszek-Leonardi
2024. Models of symbol emergence in communication: a conceptual review and a guide for avoiding local minima. Artificial Intelligence Review 58:2 DOI logo
Jones, Peter E. & Catherine Read
2023. Mythbusters united? A dialogue over Harris's integrationist linguistics and Gibson's Ecological Psychology. Language Sciences 97 ► pp. 101536 ff. DOI logo
Rączaszek-Leonardi, Joanna, Krzysztof Główka, Iris Nomikou & Nicole Rossmanith
2022. Time-to-smile, time-to-speak, time-to-resolve: timescales for shaping engagement in language. Language Sciences 93 ► pp. 101495 ff. DOI logo

This list is based on CrossRef data as of 17 march 2026. Please note that it may not be complete. Sources presented here have been supplied by the respective publishers. Any errors therein should be reported to them.

Mobile Menu Logo with link to supplementary files background Layer 1 prag Twitter_Logo_Blue