Learning Semantic Combinatoriality from the Interaction between Linguistic and Behavioral Processes  

Oleh:

Sugita, Yuuya ; Tani, Jun

Jenis: Article from Journal - e-Journal
Dalam koleksi: Adaptive Behavior vol. 13 no. 1 (Mar. 2005), page 33–52.
Topik: embodied language; compositionality; recurrent neural network; self-organization; dynamical systems; robot
Fulltext: 33.pdf (718.67KB)

Isi artikel

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.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali