Simulating Meaning Negotiation Using Observational Language Games

In this article, we study the emergence of associations between words and concepts using the self-organizing map. In particular, we explore the meaning negotiations among communicating agents. The self-organizing map is used as a model of an agent's conceptual memory. The concepts are not explicitly given but they are learned by the agent in an unsupervised manner. Concepts are viewed as areas formed in a self-organizing map based on unsupervised learning. The language acquisition process is modeled in a population of simulated agents by using a series of language games, specifically observational games. The results of the simulation experiments verify that the agents learn to communicate successfully and a shared lexicon emerges.

[1]  Luc Steels,et al.  Grounding adaptive language games in robotic agents , 1997 .

[2]  Paul Vogt,et al.  Lexicon Grounding on Mobile Robots , 2000 .

[3]  Paul Vogt,et al.  Investigating social interaction strategies for bootstrapping lexicon development , 2003, J. Artif. Soc. Soc. Simul..

[4]  Timo Honkela,et al.  Proceedings of the International and Interdisciplinary Conference on Adaptive Knowledge Representation and Reasoning (AKRR'05), Espoo, Finland, June 15-17, 2005 , 2005 .

[5]  Paul Vogt,et al.  The emergence of compositional structures in perceptually grounded language games , 2005, Artif. Intell..

[6]  Philippe G. Schyns.  A Modular Neural Network Model of Concept Acquisition , 1991 .

[7]  Stefan Wermter,et al.  Learning robot actions based on self-organising language memory , 2003, Neural Networks.

[8]  Angelo Cangelosi,et al.  The Emergence of a 'Language' in an Evolving Population of Neural Networks , 1998, Connect. Sci..

[9]  Edwin D. de Jong,et al.  Autonomous Formation of Concepts and Communication , 2000 .

[10]  Simon Kirby,et al.  Spontaneous evolution of linguistic structure-an iterated learning model of the emergence of regularity and irregularity , 2001, IEEE Trans. Evol. Comput..

[11]  Andrew D. M. Smith,et al.  Establishing Communication Systems without Explicit Meaning Transmission , 2001, ECAL.

[12]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[13]  Patrick Grim,et al.  Evolution of communication with a spatialized genetic algorithm , 1999 .

[14]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[15]  Timo Honkela,et al.  Self-Refreshing SOM as a Semantic Memory Model , 2005 .

[16]  Peter Gärdenfors,et al.  Conceptual spaces - the geometry of thought , 2000 .

[17]  L. Steels.  Perceptually grounded meaning creation , 1996 .

[18]  T. Honkela,et al.  Assessing similarity of emergent representations based on unsupervised learning , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[19]  Timo Honkela.  Neural Nets that Discuss: A General Model of Communication Based on Self-Organizing Maps , 1993 .

[20]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[21]  Wolfgang Banzhaf,et al.  Advances in Artificial Life , 2003, Lecture Notes in Computer Science.

[22]  L. Wittgenstein.  Philosophical investigations = Philosophische Untersuchungen , 1958 .

[23]  Pierre-Yves Oudeyer,et al.  The self-organization of combinatoriality and phonotactics in vocalization systems , 2005, Connect. Sci..

[24]  Luc Steels,et al.  Emergent adaptive lexicons , 1996 .