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.
Code (1)
Tasks
Dependency ParsingSemantic Role LabelingSemantic Role Labeling (predicted predicates)Similar Papers 제목 키워드 기반
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 …
Dependency ParsingSemantic Role LabelingSemantic Role Labeling as Syntactic Dependency Parsing
We reduce the task of (span-based) PropBank-style semantic role labeling (SRL) to syntactic dependency parsing. Our approach is motivated by our empirical analysis that shows three common syntactic patterns account for o…
Dependency ParsingSemantic Role LabelingCMILLS: Adapting Semantic Role Labeling Features to Dependency Parsing
Syntax-aware Semantic Role Labeling without Parsing
In this paper we focus on learning dependency aware representations for semantic role labeling without recourse to an external parser. The backbone of our model is an LSTM-based semantic role labeler jointly trained with…
ARCSemantic Role LabelingViable Dependency Parsing as Sequence Labeling
We recast dependency parsing as a sequence labeling problem, exploring several encodings of dependency trees as labels. While dependency parsing by means of sequence labeling had been attempted in existing work, results …
Dependency Parsing