Modeling interaction of syntax and semantics in language acquisition

How language is acquired by children is one of the major questions of cognitive science and is linked intimately to the larger question of how the brain and mind work. I describe a connectionist model of language comprehension that shows how some behaviors and strategies in language learning can emerge from general learning mechanisms and the interaction of syntax and semantics. A connectionist network attempts to produce the meanings of input sentences, generated by a small English-like grammar. Three interesting behaviors emerge as the network attempts to perform the task. First, the network can use syntactic cues to predict aspects of the meaning of a novel word (syntactic bootstrapping), and its learning of new syntax is aided by the knowledge of word meanings (semantic bootstrapping). When a familiar verb is input in an incorrect syntactic context, the network tends to follow context to arrive at an interpretation of the utterance in the early stages of training, and follows the verb in later stages. Similar behavior is observed in children, known as frame and verb compliance. Lastly, there is considerable evidence that children's early language is item-based, i.e., organized around specific linguistic expressions and items they hear. The network's representations are also found to be highly item-based and context-specific in early stages, and become categorical in later stages of learning, similar to those of adults. These results support the idea that domain-specific behaviors and learning strategies can emerge from interactions between relatively general mechanisms and constraints, and it is not always necessary to propose apparatus specifically designed for particular tasks and phenomena. The connectionist simulations also provide a concrete and parsimonious account of these three phenomena in language development.