Abstract
A fundamental step in sentence comprehension involves assigning semantic roles to sentence constituents. To accomplish this, the listener must parse the sentence, ?nd constituents that are candidate arguments, and assign semantic roles to those constituents. Where do children learning their ?rst languages begin in solving this problem? Even assuming children can derive a rough meaning for the sentence from the situation, how do they begin to map this meaning to the structure and the structure to the form of the sentence? In this paper we use feedback from a semantic role labeling (SRL) task to improve the intermediate syntactic representations that feed the SRL. We accomplish this by training an intermediate classi?er using signals derived from latent structure optimization techniques. By using a separate classi?er to predict internal structure we see bene?ts due to knowledge embedded in the classi?er’s feature representation. This extra structure allows the system to begin to learn using weaker, more plausible semantic feedback.