Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments
Semantic role labeling (SRL) is a fundamental yet challenging task in the NLP community. Recent works of SRL mainly fall into two lines: 1) BIO-based; 2) span-based. Despite ubiquity, they share some intrinsic drawbacks of not considering internal argument structures, potentially hindering the model's expressiveness. The key challenge is arguments are flat structures, and there are no determined subtree realizations for words inside arguments. To remedy this, in this paper, we propose to regard flat argument spans as latent subtrees, accordingly reducing SRL to a tree parsing task. In particular, we equip our formulation with a novel span-constrained TreeCRF to make tree structures span-aware and further extend it to the second-order case. We conduct extensive experiments on CoNLL05 and CoNLL12 benchmarks. Results reveal that our methods perform favorably better than all previous syntax-agnostic works, achieving new state-of-the-art under both end-to-end and w/ gold predicates settings.
PDF Abstract COLING 2022 PDF COLING 2022 AbstractCode
Datasets
Results from the Paper
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Semantic Role Labeling | CoNLL 2005 | CRF2o | F1 | 87.87 | # 8 | |
| Semantic Role Labeling | CoNLL 2005 | CRF2o + BERT | F1 | 89.03 | # 5 | |
| Semantic Role Labeling | CoNLL 2005 | CRF2o + RoBERTa | F1 | 89.54 | # 3 | |
| Semantic Role Labeling (predicted predicates) | CoNLL 2012 | CRF2O + BERT | F1 | 85.45 | # 2 | |
| Semantic Role Labeling | OntoNotes | CRF2o + BERT | F1 | 87.66 | # 5 | |
| Semantic Role Labeling | OntoNotes | CRF2o + RoBERTa | F1 | 88.32 | # 2 | |
| Semantic Role Labeling | OntoNotes | CRF2o | F1 | 83.66 | # 13 |
