An Argument-Marker Model for Syntax-Agnostic Proto-Role Labeling
This work addresses SPRL for natural language processing researchers, offering an incremental improvement by removing dependency on external resources.
The paper tackled semantic proto-role labeling (SPRL) by developing an ensemble of hierarchical models with self-attention and predicate-argument-markers, achieving competitive state-of-the-art performance in multi-label and multi-variate Likert scale prediction tasks without relying on gold argument heads from tree banks.
Semantic proto-role labeling (SPRL) is an alternative to semantic role labeling (SRL) that moves beyond a categorical definition of roles, following Dowty's feature-based view of proto-roles. This theory determines agenthood vs. patienthood based on a participant's instantiation of more or less typical agent vs. patient properties, such as, for example, volition in an event. To perform SPRL, we develop an ensemble of hierarchical models with self-attention and concurrently learned predicate-argument-markers. Our method is competitive with the state-of-the art, overall outperforming previous work in two formulations of the task (multi-label and multi-variate Likert scale prediction). In contrast to previous work, our results do not depend on gold argument heads derived from supplementary gold tree banks.