Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling
This work addresses the limitation of prior neural SRL models that require gold predicates and cannot use span-level features, offering a more practical solution for natural language processing tasks.
The paper tackles the problem of semantic role labeling (SRL) by proposing an end-to-end model that jointly predicts predicates, argument spans, and their relations, setting a new state of the art on PropBank SRL without relying on gold predicates.
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.