Semantic Role Labeling as Syntactic Dependency Parsing

TL;DR

This paper demonstrates that semantic role labeling can be effectively reformulated as a dependency parsing problem, leveraging syntactic structures to improve SRL accuracy for English and Chinese.

Contribution

It introduces a conversion scheme that encodes SRL annotations into dependency trees, enabling the use of dependency parsers for SRL with competitive performance.

Findings

Over 98% of SRL annotations are explained by three syntactic patterns.

Dependency parsing achieves state-of-the-art SRL performance.

Syntactic dependency trees effectively encode semantic roles.

Abstract

We reduce the task of (span-based) PropBank-style semantic role labeling (SRL) to syntactic dependency parsing. Our approach is motivated by our empirical analysis that shows three common syntactic patterns account for over 98% of the SRL annotations for both English and Chinese data. Based on this observation, we present a conversion scheme that packs SRL annotations into dependency tree representations through joint labels that permit highly accurate recovery back to the original format. This representation allows us to train statistical dependency parsers to tackle SRL and achieve competitive performance with the current state of the art. Our findings show the promise of syntactic dependency trees in encoding semantic role relations within their syntactic domain of locality, and point to potential further integration of syntactic methods into semantic role labeling in the future.