Semantic Role Labeling as Syntactic Dependency Parsing
This work addresses semantic role labeling for natural language processing by integrating syntactic methods, though it is incremental as it builds on existing dependency parsing techniques.
The paper tackles semantic role labeling (SRL) by reducing it to syntactic dependency parsing, based on empirical analysis showing that over 98% of SRL annotations in English and Chinese follow three common syntactic patterns, and achieves competitive performance with state-of-the-art methods.
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.