Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing

Shilin Zhou, Qingrong Xia, Zhenghua Li, Yu Zhang, Yu Hong, Min Zhang

Abstract
This paper proposes to cast end-to-end span-based SRL as a word-based graph parsing task. The major challenge is how to represent spans at the word level. Borrowing ideas from research on Chinese word segmentation and named entity recognition, we propose and compare four different schemata of graph representation, i.e., BES, BE, BIES, and BII, among which we find that the BES schema performs the best. We further gain interesting insights through detailed analysis. Moreover, we propose a simple constrained Viterbi procedure to ensure the legality of the output graph according to the constraints of the SRL structure. We conduct experiments on two widely used benchmark datasets, i.e., CoNLL05 and CoNLL12. Results show that our word-based graph parsing approach achieves consistently better performance than previous results, under all settings of end-to-end and predicate-given, without and with pre-trained language models (PLMs). More importantly, our model can parse 669/252 sentences per second, without and with PLMs respectively.
Anthology ID:
2022.coling-1.365
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:
4160–4171
Language:
URL:
https://aclanthology.org/2022.coling-1.365
DOI:
Bibkey:
Cite (ACL):
Shilin Zhou, Qingrong Xia, Zhenghua Li, Yu Zhang, Yu Hong, and Min Zhang. 2022. Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4160–4171, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing (Zhou et al., COLING 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/paclic-22-ingestion/2022.coling-1.365.pdf
Code
 zslin177/srl-as-gp
PDF Search Code