Iterative Span Selection: Self-Emergence of Resolving Orders in Semantic Role Labeling

Shuhei Kurita, Hiroki Ouchi, Kentaro Inui, Satoshi Sekine


Abstract
Semantic Role Labeling (SRL) is the task of labeling semantic arguments for marked semantic predicates. Semantic arguments and their predicates are related in various distinct manners, of which certain semantic arguments are a necessity while others serve as an auxiliary to their predicates. To consider such roles and relations of the arguments in the labeling order, we introduce iterative argument identification (IAI), which combines global decoding and iterative identification for the semantic arguments. In experiments, we first realize that the model with random argument labeling orders outperforms other heuristic orders such as the conventional left-to-right labeling order. Combined with simple reinforcement learning, the proposed model spontaneously learns the optimized labeling orders that are different from existing heuristic orders. The proposed model with the IAI algorithm achieves competitive or outperforming results from the existing models in the standard benchmark datasets of span-based SRL: CoNLL-2005 and CoNLL-2012.
Anthology ID:
2022.coling-1.478
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:
5383–5397
Language:
URL:
https://aclanthology.org/2022.coling-1.478
DOI:
Bibkey:
Cite (ACL):
Shuhei Kurita, Hiroki Ouchi, Kentaro Inui, and Satoshi Sekine. 2022. Iterative Span Selection: Self-Emergence of Resolving Orders in Semantic Role Labeling. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5383–5397, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Iterative Span Selection: Self-Emergence of Resolving Orders in Semantic Role Labeling (Kurita et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.478.pdf