A constraint-based lexicalist account of the subject/object attachment preference

When a noun phrase could either be the object of the preceding verb or the subject of a new clause or a sentence complement, readers and listeners show a strong preference to parse the noun phrase as the object of the verb. This can result in clear garden paths for sentences such asThe student read the book was stolen andWhile the student read the book was stolen. Even when the verb does not permit a noun phrase complement, soem processing difficulty is still found. This has led some theorists to propose models in which initial attachments are lexically blind, with lexical information subsequently used as a filter to evaluate and revise initial analyses. In contrast, we show that these results emerge naturally from constraint-based lexicalist models. We present a modeling experiment with a simple recurrent network that was trained to predict upcoming complements for a sample of verbs taken from the Penn Treebank corpus. The model exhibits an boject bias and it aloo shows effects of verb frequency which are similar to those found in the psycholinguistic literature.