Verb frame frequency as a predictor of verb bias.

There is considerable evidence showing that the human sentence processor is guided by lexical preferences in resolving syntactic ambiguities. Several types of preferences have been identified, including morphological, syntactic, and semantic ones. However, the literature fails to provide a uniform account of what lexical preferences are and how they should be measured. The present paper provides evidence for the view that lexical preferences are records of prior linguistic experience. We show that a type of lexial syntactic preference, viz., verb biases as measured by norming experiments, can be approximated by verb frame frequencies extracted from a large, balanced corpus using computational learning techniques.