Natural language acquisition in large scale neural semantic networks

This thesis puts forward the view that a purely signal-based approach to natural language processing is both plausible and desirable. By questioning the veracity of symbolic representations of meaning, it argues for a unified, non-symbolic model of knowledge representation that is both biologically plausible, and potentially, highly efficient.Processes to generate a grounded, neural form of this model - dubbed the semantic filter - are discussed. The combined effects of local neural organisation, coincident with perceptual maturation, are used to hypothesise its nature. This theoretical model is then validated in light of a number of fundamental neurological constraints and milestones. The mechanisms of semantic and episodic development that the model predicts are then used to explain linguistic properties, such as propositions and verbs, syntax and scripting.To mimic the growth of locally densely connected structures upon an unbounded neural substrate, a system is developed that can grow arbitrarily large, data-dependent structures composed of individual self-organising neural networks. The maturational nature of the data used results in a structure in which the perception of concepts is refined by the networks, but demarcated by subsequent structure. As a consequence, the overall structure shows significant memory and computation benefits, as predicted by the cognitive and neural models. Furthermore, the localised nature of the neural architecture also avoids the increasing error sensitivity and redundancy of traditional systems as the training domain grows. The semantic and episodic filters have been demonstrated to perform as well, or better, than more specialist networks, whilst using significantly larger vocabularies, more complex sentence forms and more natural corpora.