Command Palette
Search for a command to run...
Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling
Luheng He; Kenton Lee; Omer Levy; Luke Zettlemoyer
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.
Code Repositories
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| semantic-role-labeling-on-conll-2005 | He et al. (2018) + ELMo | F1: 86.0 |
| semantic-role-labeling-on-conll-2005 | He et al. (2018) | F1: 82.5 |
| semantic-role-labeling-on-ontonotes | He et al. | F1: 82.1 |
| semantic-role-labeling-on-ontonotes | He et al., | F1: 85.5 |
| semantic-role-labeling-predicted-predicates | He et al. 2018 + ELMo | F1: 86.0 |
| semantic-role-labeling-predicted-predicates | He et al. (2018) | F1: 86.0 |
| semantic-role-labeling-predicted-predicates | He et al. 2018 | F1: 82.5 |
| semantic-role-labeling-predicted-predicates-1 | He et al. 2018 + ELMo | F1: 82.9 |
| semantic-role-labeling-predicted-predicates-1 | He et al. 2018 | F1: 79.8 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.