Tree Representations for Chinese Semantic Role Labeling

We compare different parse tree representa- tions for the task of Chinese Semantic Role Labeling (SRL), including dependency and constituency parse trees, two tree pruning methods, and neighbor features. Three learn- ing models are compared. By using SVM clas- sifier with neighbor features and pruning tree to phrase level we achieve significantly better speed and accuracy than state of the art Chi- nese SRL systems.