登入選單
返回Google圖書搜尋
Compositionality and Systematicity in Connectionist Language Learning
註釋Fodor and Pylyshyn (1988) argue in their paper that connectionist networks, as they are commonly constructed and trained, are incapable of displaying certain crucial characteristics of human thought and language. These include the capacity to employ compositionally structured representations and to exhibit systemacity in thought and language production. Since the appearance of Fodor and Pylyshyn's paper, a number of connectionists have produced what purports to be counter-examples to the Fodor-Pylyshyn thesis. This paper examines several of these purported counter-examples. It is argued that although these networks appear to discover a degree of compositionality, and to display a degree of systematic behaviour, the degrees involved are substantially less than that found in humans, and consequently are less than what Fodor and Pylyshyn require.