The necessity of parsing for predicate argument recognition

Broad-coverage corpora annotated with semantic role, or argument structure, information are becoming available for the first time. Statistical systems have been trained to automatically label semantic roles from the output of statistical parsers on unannotated text. In this paper, we quantify the effect of parser accuracy on these systems' performance, and examine the question of whether a flatter "chunked" representation of the input can be as effective for the purposes of semantic role identification.