Integrating Cluster Information for Cross-Frame Semantic Role Labeling
Shan He, Daniel Gildea · UR Research (University of Rochester) · 2006
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. This material is based upon work supported by from the National Institute of Health grant number 2ROERR09283-