English

Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling

Computation and Language 2018-08-14 v2

Abstract

Recent BIO-tagging-based neural semantic role labeling models are very high performing, but assume gold predicates as part of the input and cannot incorporate span-level features. We propose an end-to-end approach for jointly predicting all predicates, arguments spans, and the relations between them. The model makes independent decisions about what relationship, if any, holds between every possible word-span pair, and learns contextualized span representations that provide rich, shared input features for each decision. Experiments demonstrate that this approach sets a new state of the art on PropBank SRL without gold predicates.

Keywords

Cite

@article{arxiv.1805.04787,
  title  = {Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling},
  author = {Luheng He and Kenton Lee and Omer Levy and Luke Zettlemoyer},
  journal= {arXiv preprint arXiv:1805.04787},
  year   = {2018}
}

Comments

5 pages, ACL 2018

R2 v1 2026-06-23T01:53:02.915Z