Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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.

Zuchao Li, Shexia He, Hai Zhao, Yiqing Zhang, Zhuosheng Zhang, Xi Zhou, Xiang Zhou• 2019

Related benchmarks

TaskDatasetResultRank
Span-based Semantic Role LabelingCoNLL 2005 (Out-of-domain (Brown))
F1 Score80.5
41
Semantic Role LabelingCoNLL 2005 (WSJ)
F1 Score87.7
41
Dependency Semantic Role LabelingCoNLL 2009 (test)
F1 Score90.4
32
Semantic Role LabelingCoNLL WSJ English benchmark 2009 (test)
F1 Score90.4
31
Semantic Role LabelingCoNLL 2005 (Brown)
F1 Score76.4
31
Semantic Role LabelingCoNLL English Brown 2009 (test)
F1 Score81.5
28
Span Semantic Role LabelingCoNLL-2012 (OntoNotes) v5.0 (test)
F1 Score86
25
Semantic Role LabelingCoNLL 2005 (WSJ (in-domain))
F1 Score87.7
24
Dependency-based Semantic Role LabelingCoNLL Brown 2009 (test)
Precision81.7
22
Semantic Role LabelingCoNLL 2012
F1 Score83.1
21
Showing 10 of 28 rows

Other info

Code

Follow for update