Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures inside Arguments
Yu Zhang, Qingrong Xia, Shilin Zhou, Yong Jiang, Guohong Fu, Min Zhang
Abstract
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.- Anthology ID:
- 2022.coling-1.370
- Volume:
- Proceedings of the 29th International Conference on Computational Linguistics
- Month:
- October
- Year:
- 2022
- Address:
- Gyeongju, Republic of Korea
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 4212–4227
- Language:
- URL:
- https://aclanthology.org/2022.coling-1.370
- DOI:
- Cite (ACL):
- Yu Zhang, Qingrong Xia, Shilin Zhou, Yong Jiang, Guohong Fu, and Min Zhang. 2022. Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures inside Arguments. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4212–4227, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
- Cite (Informal):
- Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures inside Arguments (Zhang et al., COLING 2022)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2022.coling-1.370.pdf
- Code
- yzhangcs/crfsrl
- Data
- CoNLL-2012, OntoNotes 5.0