Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling
Luheng Hea b, Kenton Leea b, Omer Levya b, Luke Zettlemoyera b
- aSchool of Computer Science & Engineering University of Washington , Seattle WA
- bSchool of Computer Science & Engineering University of Washington, Seattle WA
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
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 endto-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. 1
TL;DRThis work proposes an end-to-end approach for jointly predicting all predicates, arguments spans, and the relations between them, and makes independent decisions about what relationship, if any, holds between every possible word-span pair. (Semantic Scholar)