Neural-Davidsonian Semantic Proto-role Labeling
Rachel Rudinger, Adam Teichert, Ryan Culkin, Sheng Zhang, Benjamin Van Durme
Abstract
We present a model for semantic proto-role labeling (SPRL) using an adapted bidirectional LSTM encoding strategy that we call NeuralDavidsonian: predicate-argument structure is represented as pairs of hidden states corresponding to predicate and argument head tokens of the input sequence. We demonstrate: (1) state-of-the-art results in SPRL, and (2) that our network naturally shares parameters between attributes, allowing for learning new attribute types with limited added supervision.- Anthology ID:
- D18-1114
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 944–955
- Language:
- URL:
- https://aclanthology.org/D18-1114
- DOI:
- 10.18653/v1/D18-1114
- Cite (ACL):
- Rachel Rudinger, Adam Teichert, Ryan Culkin, Sheng Zhang, and Benjamin Van Durme. 2018. Neural-Davidsonian Semantic Proto-role Labeling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 944–955, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Neural-Davidsonian Semantic Proto-role Labeling (Rudinger et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/D18-1114.pdf
- Code
- decomp-sem/neural-sprl