Research And Application Of A Computational Model Of Child's Simple Syntax Acquisition

This paper proposes several factors for computational models of early child language acquisition, giving a better explanation on how external language input and intrinsic parameter affect learning, comprehension and production of simple syntax. Taking a model simulating transition from one-word stage to two-word stage (O2T) as beginning, the paper gives quantitative simulation based investigations on how the language input and parameter affect the volume of system (i.e. how much is learned) and evaluation output (i.e. how well the learned can be used by the system to comprehend or produce simple syntax). Factors including contributing word, related string/concept and critical abstract factor, have been figured out to uncover underlying reasons. Contributing words bring syntax information from language input to the system; related strings/concepts relate the learned syntax to new syntax; and abstract factor is crucial for the ability of generative learning. Experiment results show that contributing word and related string/concept have much greater influence respectively on the volume of system and evaluation output, compared to other information the language input contains. Jointly with related string/concept, critical abstract factor controls evaluation output. And there exists value ranges of critical abstract factor for the occurrence of under-extension and over-extension. After that, the paper makes similar investigation on MOSAIC (i.e. a mature and widely-accepted computational model of syntax acquisition), and get similar results, which indicate some degree of generality of the factors. In the light of discrepancies between the results, the paper also gets a clearer image of MOSAIC by discussing its differences from O2T model. By introducing visual features to O2T model, we develop a V-O2T system, based on which a picture-aid early learning software is designed to evaluate child's ability of generative learning.