Zuchao Li, Shexia He, Hai Zhao, Yiqing Zhang, Zhuosheng Zhang, Xi Zhou, Xiang Zhou
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.
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Semantic Role Labeling | OntoNotes | F1 | 86 | Li et al. |
| Semantic Role Labeling | CoNLL 2005 | F1 | 87.7 | Li et al. (2019) (Ensemble) |
| Semantic Role Labeling | CoNLL 2005 | F1 | 86.3 | Li et al. (2019) + ELMo |
| Semantic Role Labeling | CoNLL 2005 | F1 | 83 | Li et al. (2019) |