Dependency or Span, End-to-End Uniform Semantic Role Labeling


  • Zuchao Li Shanghai Jiao Tong University
  • Shexia He Shanghai Jiao Tong University
  • Hai Zhao Shanghai Jiao Tong University
  • Yiqing Zhang Shanghai Jiao Tong University
  • Zhuosheng Zhang Shanghai Jiao Tong University
  • Xi Zhou CloudWalk Technology
  • Xiang Zhou CloudWalk Technology



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.




How to Cite

Li, Z., He, S., Zhao, H., Zhang, Y., Zhang, Z., Zhou, X., & Zhou, X. (2019). Dependency or Span, End-to-End Uniform Semantic Role Labeling. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 6730-6737.



AAAI Technical Track: Natural Language Processing