Distributed Representations for Unsupervised Semantic Role Labeling

Kristian Woodsend, Mirella Lapata

Abstract: We present a new approach for unsupervised semantic role labeling that leverages distributed representations. We induce embeddings to represent a predicate, its arguments and their complex interdependence. Argument embeddings are learned from surrounding contexts involving the predicate and neighboring arguments, while predicate embeddings are learned from argument contexts. The induced representations are clustered into roles using a linear programming formulation of hierarchical clustering, where we can model task-specific knowledge. Experiments show improved performance over previous unsupervised semantic role labeling approaches and other distributed word representation models.