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 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Semantic Role Labeling CoNLL 2005 CRF2o F1 87.87 # 7
Semantic Role Labeling CoNLL 2005 CRF2o + BERT F1 89.03 # 4
Semantic Role Labeling CoNLL 2005 CRF2o + RoBERTa F1 89.54 # 3
Semantic Role Labeling OntoNotes CRF2o + RoBERTa F1 88.32 # 1
Semantic Role Labeling OntoNotes CRF2o F1 83.66 # 12
Semantic Role Labeling OntoNotes CRF2o + BERT F1 87.66 # 4

Methods


No methods listed for this paper. Add relevant methods here