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 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.- Anthology ID:
- P18-2058
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 364–369
- Language:
- URL:
- https://aclanthology.org/P18-2058
- DOI:
- 10.18653/v1/P18-2058
- Cite (ACL):
- Luheng He, Kenton Lee, Omer Levy, and Luke Zettlemoyer. 2018. Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 364–369, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling (He et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/P18-2058.pdf
- Code
- luheng/lsgn
- Data
- CoNLL-2012, OntoNotes 5.0