A review of statistical and cognitive learning for sentence processing

Abstract

In the research field of natural language processing (NLP), sentence stands a very prominent position in text processing. The procedure of sentence processing acquires technologies at a higher level, such as computing the meaning of a sentence based on analysis of meanings of its individual words. This paper reviews several typical research works for statistical learning, highlights relevant cognitive concepts and models, introduces a cognitive sentence parser based on Simple Recurrent Networks (SRNs), and concludes that further research should be implemented with more cognitive models.