We present a novel connectionist model for acquiring the semantics of a simple language through the behavioral experiences of a real robot. We focus on the “compositionality” of semantics and examine how it can be generated through experiments. Our experimental results showed that the essential structures for situated semantics can self-organize themselves through dense interactions between linguistic and behavioral processes whereby a certain generalization in learning is achieved. Our analysis of the acquired dynamical structures indicates that an equivalence of compositionality appears in the combinatorial mechanics self-organized in the neuronal nonlinear dynamics. The manner in which this mechanism of compositionality, based on dynamical systems, differs from that considered in conventional linguistics and other synthetic computational models, is discussed in this paper.
Arbib, M. (2002). The mirror system, imitation, and the evolution of language. In K. Dautenhahn & C. L. Nehaniv (Eds.), Imitation in animals and artifacts (pp. 229-280). Cambridge, MA: MIT Press .
2.
Arkin, R. C. (1998). Behavior-based robotics. Cambridge, MA: MIT Press .
3.
Beer, R. (1995). A dynamical systems perspective on agent-environment interaction . Artificial Intelligence, 72(1), 173-215 .
4.
Billard, A. (2002). Imitation: A means to enhance learning of a synthetic proto-language in an autonomous robot. In K. Dautenhahn & C. L. Nehaniv (Eds.), Imitation in animals and artifacts (pp. 281-311). Cambridge, MA: MIT Press .
5.
Cangelosi, A. (2004). The sensorimotor bases of linguistic structure: experiments with grounded adaptive agents . In S. Schaalet al. (Ed.), From animals to animats 8: Proceedings of the Eighth International Conference on Simulation of Adaptive Behavior (pp. 487-496 ). Cambridge, MA: MIT Press.
6.
Elman, J. (1990). Finding structure in time . Cognitive Science, 14, 179-211 .
7.
Evans, G. (1981). Semantic theory and tacit knowledge. In S. Holzman & C. Leich (Eds.), Wittgenstein: To follow a rule (pp. 118-137). London: Routledge and Kegan Paul .
8.
Gelder, T. van . (1998). The dynamical hypothesis in cognitive science . Behavior and Brain Sciences, 27(5), 615-628 .
9.
Hadley, R. (1994). Systematicity revisited: Reply to Christiansen and Chater and Niklasson and van Gelder . Mind and Language, 9, 431-444 .
10.
Harnad, S. (1990). The symbol grounding problem . Physica D, 42, 335-346 .
11.
Ito, M. , & Tani, J. (2004a). Generalization in learning multiple temporal patterns using RNNPB . In Proceedings of the 11th International Conference on Neural Information Processing (ICONIP’ 04) (in press).
12.
Ito, M. , & Tani, J. (2004b). On-line imitative interaction with a humanoid robot using a dynamic neural network model of a mirror system . Adaptive Behavior (in press).
13.
Iwahashi, N. (2003). Language acquisition by robots—towards a new paradigm of language processing . Journal of Japanese Society for Artificial Intelligence, 48(1), 49-58 .
14.
Jordan, M. , & Rumelhart, D. (1992). Forward models: Supervised learning with a distal teacher . Cognitive Science, 16, 307-354 .
15.
Kawato, M. , Furukawa, K. , & Suzuki, R. (1987). A hierarchical neural network model for the control and learning of voluntary movement . Biological Cybernetics, 57, 169-185 .
16.
Kirby, S. , & Hurford, J. (2002). The emergence of linguistic structure: An overview of the iterated learning model. In D. Parisi & A. Cangelosi (Eds.), Simulating The Evolution of Language (pp. 121-148). London: Springer .
17.
Kuipers, B. , & Byun, Y. T. (1987). A qualitative approach to robot exploration and map-learning . In IEEE workshop on spatial reasoning and multi-sensor fusion (pp. 390-404 ). Los Altos, CA: IEEE.
18.
Mataric, M. (1992). Integration of representation into goal-driven behavior-based robot . IEEE Transactions on Robotics and Automation, 8(3), 304-312 .
19.
Miikkulainen, R. (1993). Cambridge, MA: MIT Press.
20.
Pollack, J. (1991). The induction of dynamical recognizers . Machine Learning, 7, 227-252 .
21.
Rizzolatti, G. , Fadiga, L. , Galles, B. , & Fogassi, L. (1996). Promotor cortex and the recognition of motor actions . Cognitive Brain Research, 3, 131-141 .
22.
Roy, D. (2002). Learning visually grounded words and syntax for a scene description task . Computer Speech and Language, 16, 353-385 .
23.
Rumelhart, D. , Hinton, G. , & Williams, R. (1986). Learning internal representations by error propagation. In D. Rumelhart & J. Mclelland (Eds.), Parallel distributed processing (Vol. 1, pp. 318-362). Cambridge, MA: MIT Press .
24.
Schoner, S. , & Kelso, S. (1988). Dynamic pattern generation in behavioral and neural systems . Science, 239, 1513-1519 .
25.
Siskind, J. (2001). Grounding the Lexical Semantics of Verbs in Visual Perception using Force Dynamics and Event Logic . Artificial Intelligence Research, 15, 31-90 .
26.
Steels, L. (2000). The emergence of grammar in communicating autonomous robotic agents. In W. Horn (Ed.), Proceedings of ECAI 2000: 14th European Conference on Artificial Intelligence (Vol. 54, pp. 764-769). Amsterdam: IOS Press .
27.
Steels, L. (2002). Grounding symbols through evolutionary language games. In A. Cangelosi & D. Parisi (Eds.), Simulating the evolution of language (pp. 211-226). London: Springer .
28.
Steels, L. , & Vogt, P. (1997). Grounding adaptive language games in robotic agents . In P. Husbands & I. Harvey (Eds.), Proceedings of the Fourth European Conference on Artificial Life, ECAL’97 (pp. 474-482 ). Cambridge, MA: MIT Press.
29.
Sugita, Y. , & Tani, J. (2002). A connectionist model which unifies the behavioral and the linguistic processes: Results from robot learning experiments. In M. Stamenov & V. Gallese (Eds.), Mirror neurons and the evolution of brain and language (pp. 363-376). Amsterdam/Philadelphia: John Benjamins .
30.
Tani, J. (1996). Model-based learning for mobile robot navigation from the dynamical systems perspective . IEEE Transactions on Systems, Man and Cybernetics, Part B, 26(3), 421-436 .
31.
Tani, J. (2003). Learning to generate articulated behavior through the bottom-up and the top-down interaction process . Neural Networks, 16, 11-23 .
32.
Tani, J. , & Ito, M. (2003). Self-organization of behavioral primitives as multiple attractor dynamics: A robot experiment . IEEE Transactions on Systems, Man and Cybernetics, Pan A, 33(4), 481-488 .
33.
Tani, J. , & Nolfi, S. (1999). Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems . Neural Networks, 12, 1131-1141 .
34.
Thompson, C. A. , & Mooney, R. J. (1998). Semantic lexicon acquisition for learning natural language interfaces (Tech. Rep. No. AI98-273). The University of Texas at Austin .
35.
Vogt, P. (2003). Iterated learning and grounding from holistic to compositional languages . In S. Kirby (Ed.), Language evolution and computation, Proceedings of the Workshop/Course at ESSLLI (pp. 76-86 ).
36.
Wiggins, S. (1990). Introduction to applied nonlinear dynamical systems and chaos. New York: Springer .
37.
Wiles, J. , Blair, A. , & Boden, M. (2001). Representation Beyond Finite States: Alternatives to Push-Down Automata. In J. F. Kolen & S. C. Kremer (Eds.), A field guide to dynamical recurrent networks (pp. 129-142). New York: IEEE Press .
38.
Winograd, T. (1972). Understanding natural language . Cognitive Psychology, 3(1), 1-191 .
