Semantic role labeling aims to model the predicate-argument structure of a sentence and is often described as answering "Who did what to whom". BIO notation is typically used for semantic role labeling.
Example:
| Housing | starts | are | expected | to | quicken | a | bit | from | August’s | pace |
|---|---|---|---|---|---|---|---|---|---|---|
| B-ARG1 | I-ARG1 | O | O | O | V | B-ARG2 | I-ARG2 | B-ARG3 | I-ARG3 | I-ARG3 |
Models are typically evaluated on the OntoNotes benchmark based on F1.
| Model | F1 | Paper / Source | Code |
|---|---|---|---|
| Tian et al., (2022) + XLNet | 87.67 | Syntax-driven Approach for Semantic Role Labeling | Official |
| He et al., (2018) + ELMO | 85.5 | Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling | |
| (He et al., 2017) + ELMo (Peters et al., 2018) | 84.6 | Deep contextualized word representations | |
| Tan et al. (2018) | 82.7 | Deep Semantic Role Labeling with Self-Attention | |
| He et al. (2018) | 82.1 | Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling | |
| He et al. (2017) | 81.7 | Deep Semantic Role Labeling: What Works and What’s Next |
Models are typically evaluated on the CoNLL-2005 dataset based on F1.
| Model | F1 | Paper / Source | Code |
|---|---|---|---|
| Tian et al., (2022) + XLNet | 89.80 | Syntax-driven Approach for Semantic Role Labeling | Official |
| He et al., (2018) + ELMO | 87.4 | Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling | |
| He et al. (2018) | 83.9 | Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling | |
| Tan et al. (2018) | 82.9 | Deep Semantic Role Labeling with Self-Attention | |
| He et al. (2017) | 81.5 | Deep Semantic Role Labeling: What Works and What’s Next |