Dependency-based semantic role labeling using sequence labeling with a structural SVM

Semantic Role Labeling (SRL) systems aim at determining the semantic role labels of the arguments of the predicates in natural language text. SRL systems can usually be built to work upon the result of constitient analysis (constituent-based), or dependency parsing (dependency-based). SRL systems can use either classification or sequence labeling as the main processing mechanism. In this paper, we show that a dependency-based SRL system using sequence labeling can achieve state-of-the-art performance when a new structural SVM adapted from the Pegasos algorithm is exploited for performing sequence labeling.

► We proposed to use sequence labeling in “dependency-based” SRL for the first time.
► For sequence labeling, we used a Modified Pegasos algorithm as a structural SVM.
► We can use one less number of steps compared with classification based approaches.
► Our system outperforms any systems appeared in CoNLL-2008, 2009 conferences.
► Our method is much faster and requires less memory than those using CRF or ME.