An MRC Framework for Semantic Role Labeling

Nan Wang, Jiwei Li, Yuxian Meng, Xiaofei Sun, Han Qiu, Ziyao Wang, Guoyin Wang, Jun He


Abstract
Semantic Role Labeling (SRL) aims at recognizing the predicate-argument structure of a sentence and can be decomposed into two subtasks: predicate disambiguation and argument labeling. Prior work deals with these two tasks independently, which ignores the semantic connection between the two tasks. In this paper, we propose to use the machine reading comprehension (MRC) framework to bridge this gap. We formalize predicate disambiguation as multiple-choice machine reading comprehension, where the descriptions of candidate senses of a given predicate are used as options to select the correct sense. The chosen predicate sense is then used to determine the semantic roles for that predicate, and these semantic roles are used to construct the query for another MRC model for argument labeling. In this way, we are able to leverage both the predicate semantics and the semantic role semantics for argument labeling. We also propose to select a subset of all the possible semantic roles for computational efficiency. Experiments show that the proposed framework achieves state-of-the-art or comparable results to previous work.
Anthology ID:
2022.coling-1.191
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:
2188–2198
Language:
URL:
https://aclanthology.org/2022.coling-1.191
DOI:
Bibkey:
Cite (ACL):
Nan Wang, Jiwei Li, Yuxian Meng, Xiaofei Sun, Han Qiu, Ziyao Wang, Guoyin Wang, and Jun He. 2022. An MRC Framework for Semantic Role Labeling. In Proceedings of the 29th International Conference on Computational Linguistics, pages 2188–2198, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
An MRC Framework for Semantic Role Labeling (Wang et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.191.pdf
Code
 shannonai/mrc-srl
Data
OntoNotes 5.0