A Connectionist Approach to Learn Association between Sentences and Behavioral Patterns of a Robot

Abstract

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, a fundamental characteristic of human language, which is the ability to understand the meaning of a sentence as a combination of the meanings of words. We also pay much attention to the “embodiment” of a robot, which means that the robot should acquire semantics which matches its body, or sensory-motor system. The essential claim is that an embodied compositional semantic representation can be selforganized from generalized correspondences between sentences and behavioral patterns. This claim is examined and confirmed through simpie experiments in which a robot generates corresponding behaviors from unlearned sentences by analogy with the correspondences between learned sentences and behaviors.