Dependency or Span, End-to-End Uniform Semantic Role Labeling
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Span-based Semantic Role Labeling | CoNLL 2005 (Out-of-domain (Brown)) | F1 Score80.5 | 41 | |
| Semantic Role Labeling | CoNLL 2005 (WSJ) | F1 Score87.7 | 41 | |
| Dependency Semantic Role Labeling | CoNLL 2009 (test) | F1 Score90.4 | 32 | |
| Semantic Role Labeling | CoNLL WSJ English benchmark 2009 (test) | F1 Score90.4 | 31 | |
| Semantic Role Labeling | CoNLL 2005 (Brown) | F1 Score76.4 | 31 | |
| Semantic Role Labeling | CoNLL English Brown 2009 (test) | F1 Score81.5 | 28 | |
| Span Semantic Role Labeling | CoNLL-2012 (OntoNotes) v5.0 (test) | F1 Score86 | 25 | |
| Semantic Role Labeling | CoNLL 2005 (WSJ (in-domain)) | F1 Score87.7 | 24 | |
| Dependency-based Semantic Role Labeling | CoNLL Brown 2009 (test) | Precision81.7 | 22 | |
| Semantic Role Labeling | CoNLL 2012 | F1 Score83.1 | 21 |