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
Bibkey:
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)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/D18-1114.pdf
Video:
 https://vimeo.com/305214361
Code
 decomp-sem/neural-sprl