Abstract
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 pre- diction). In contrast to previous work, our results do not depend on gold argument heads derived from supplementary gold tree banks.- Anthology ID:
- S19-1025
- Volume:
- Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Venue:
- *SEM
- SIGs:
- SIGSEM | SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 224–234
- Language:
- URL:
- https://aclanthology.org/S19-1025
- DOI:
- 10.18653/v1/S19-1025
- Cite (ACL):
- Juri Opitz and Anette Frank. 2019. An Argument-Marker Model for Syntax-Agnostic Proto-Role Labeling. In Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019), pages 224–234, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- An Argument-Marker Model for Syntax-Agnostic Proto-Role Labeling (Opitz & Frank, *SEM 2019)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/S19-1025.pdf