A Double-Graph Based Framework for Frame Semantic Parsing

Ce Zheng, Xudong Chen, Runxin Xu, Baobao Chang


Abstract
Frame semantic parsing is a fundamental NLP task, which consists of three subtasks: frame identification, argument identification and role classification. Most previous studies tend to neglect relations between different subtasks and arguments and pay little attention to ontological frame knowledge defined in FrameNet. In this paper, we propose a Knowledge-guided Incremental semantic parser with Double-graph (KID). We first introduce Frame Knowledge Graph (FKG), a heterogeneous graph containing both frames and FEs (Frame Elements) built on the frame knowledge so that we can derive knowledge-enhanced representations for frames and FEs. Besides, we propose Frame Semantic Graph (FSG) to represent frame semantic structures extracted from the text with graph structures. In this way, we can transform frame semantic parsing into an incremental graph construction problem to strengthen interactions between subtasks and relations between arguments. Our experiments show that KID outperforms the previous state-of-the-art method by up to 1.7 F1-score on two FrameNet datasets. Our code is availavle at https://github.com/PKUnlp-icler/KID.
Anthology ID:
2022.naacl-main.368
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4998–5011
Language:
URL:
https://aclanthology.org/2022.naacl-main.368
DOI:
10.18653/v1/2022.naacl-main.368
Bibkey:
Cite (ACL):
Ce Zheng, Xudong Chen, Runxin Xu, and Baobao Chang. 2022. A Double-Graph Based Framework for Frame Semantic Parsing. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4998–5011, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
A Double-Graph Based Framework for Frame Semantic Parsing (Zheng et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.368.pdf
Video:
 https://aclanthology.org/2022.naacl-main.368.mp4
Code
 pkunlp-icler/kid
Data
FrameNet