Dependency-based semantic role labeling of PropBank

We present a PropBank semantic role labeling system for English that is integrated with a dependency parser.
To tackle the problem of joint syntactic-semantic analysis, the system relies on a syntactic and a semantic subcomponent. The syntactic model is a projective parser using pseudo-projective transformations, and the semantic model uses global inference mechanisms on top of a pipeline of classifiers. The complete syntactic-semantic output is selected from a candidate pool generated by the subsystems.

We evaluate the system on the CoNLL-2005 test sets using segment-based and dependency-based metrics. Using the segment-based CoNLL-2005 metric, our system achieves a near state-of-the-art F1 figure of 79.90 on the WSJ test set, or 80.67 if punctuation is treated consistently. Using a dependency-based metric, the F1 figure of our system is 85.93 on the WSJ test set from CoNLL-2008 and 73.43 on the Brown test set. Our system is the first dependency-based semantic role labeler for PropBank that rivals constituent-based systems in terms of performance.