Collective semantic role labeling on open news corpus by leveraging redundancy

Abstract

We propose a novel MLN-based method that collectively conducts SRL on groups of news sentences. Our method is built upon a baseline SRL, which uses no parsers and leverages redundancy. We evaluate our method on a manually labeled news corpus and demonstrate that news redundancy significantly improves the performance of the baseline, e.g., it improves the F-score from 64.13% to 67.66%.