Dependency or Span, End-to-End Uniform Semantic Role Labeling
This work addresses the challenge of unifying two different SRL annotation formats for researchers in natural language processing, though it is incremental in improving existing methods.
The paper tackles the problem of semantic role labeling (SRL) by developing an end-to-end model that uniformly handles both dependency-based and span-based representations, achieving new state-of-the-art results on benchmarks like CoNLL 2005, 2012, 2008, and 2009.
Semantic role labeling (SRL) aims to discover the predicateargument structure of a sentence. End-to-end SRL without syntactic input has received great attention. However, most of them focus on either span-based or dependency-based semantic representation form and only show specific model optimization respectively. Meanwhile, handling these two SRL tasks uniformly was less successful. This paper presents an end-to-end model for both dependency and span SRL with a unified argument representation to deal with two different types of argument annotations in a uniform fashion. Furthermore, we jointly predict all predicates and arguments, especially including long-term ignored predicate identification subtask. Our single model achieves new state-of-the-art results on both span (CoNLL 2005, 2012) and dependency (CoNLL 2008, 2009) SRL benchmarks.