Integrating Cluster Information for Cross-Frame Semantic Role Labeling

Recent systems for semantic role labeling are very dependent on the specific predicates and corpora on which they are trained, but labeling new data is expensive. We study which features and classifiers are best able to generalize to unseen predicates from new semantic frames. We find that automatically derived cluster information is especially helpful in this setting, and that a relatively simple a posteriori classifier outperforms Maximum Entropy