Words, Symbols, and Symbol Grounding

In this paper we present a deenition of`symbol' in cognitive science which is designed to clear some obvious misunderstandings in discussions around \symbolic" vs. \sub-symbolic" approaches. We discuss this deenition in the light of three diierent frames of reference (i.e. three diierent views, namely the intelligent agent's, an observer's, and a meta-observer's). Then we show the implications of these views for cognitive science and artiicial intelligence (AI) and discuss whether the most conspicous \symbols" in cognition { words in a language { can fullll the ideals behind their deenition.