An Epigenetic Approach to Semantic Categories

摘要

It is argued that early language learning in children emerges from five primary knowledge structures: 1) space; 2) objects; 3) actions; 4) number; and 5) events. These structures constitute the basis for the semantic domains that are used to form categories that represent the meanings of early words. The domains are naturally modeled in conceptual spaces that are based on geometric notions rather than on symbolic representations. It is shown how these semantics domains can be used to generate an epigenetic model of language acquisition. The four first primary knowledge systems are used for prepositions, nouns, verbs, and quantifiers, respectively, while events form the meanings of declarative sentences. This semantic model leads to direct recommendations for how the model can be implemented in robots and other artificial systems.