Luheng He, Kenton Lee, Omer Levy, Luke Zettlemoyer
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.
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Semantic Role Labeling | OntoNotes | F1 | 85.5 | He et al., |
| Semantic Role Labeling | OntoNotes | F1 | 82.1 | He et al. |
| Semantic Role Labeling | CoNLL 2005 | F1 | 86 | He et al. (2018) + ELMo |
| Semantic Role Labeling | CoNLL 2005 | F1 | 82.5 | He et al. (2018) |
| Semantic Role Labeling | CoNLL 2005 | F1 | 86 | He et al. 2018 + ELMo |
| Semantic Role Labeling | CoNLL 2005 | F1 | 86 | He et al. (2018) |
| Semantic Role Labeling | CoNLL 2005 | F1 | 82.5 | He et al. 2018 |
| Semantic Role Labeling | CoNLL 2012 | F1 | 82.9 | He et al. 2018 + ELMo |
| Semantic Role Labeling | CoNLL 2012 | F1 | 79.8 | He et al. 2018 |