Learning Semantic Combinatoriality from the Interaction between Linguistic and Behavioral Processes

• Yuuya Sugita

  BSI RIKEN, Japan,

• Jun Tani

  BSI RIKEN, Japan,

抄録

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.

収録刊行物

• Adaptive Behavior

  Adaptive Behavior 13 (1), 33-52, 2005-03

  SAGE Publications

キーワード

• Behavioral Neuroscience
• Experimental and Cognitive Psychology

詳細情報

• CRID: 1360574095061779584
• NII論文ID: 30007042026
• DOI: 10.1177/105971230501300102
• ISSN: 17412633
• ISSN: 10597123
• Web Site: http://journals.sagepub.com/doi/pdf/10.1177/105971230501300102
• データソース種別:
  • Crossref
  • CiNii Articles