Acquiring Frame Element Knowledge with Deep Metric Learning for Semantic Frame Induction

Kosuke Yamada, Ryohei Sasano, Koichi Takeda


Abstract
The semantic frame induction tasks are defined as a clustering of words into the frames that they evoke, and a clustering of their arguments according to the frame element roles that they should fill. In this paper, we address the latter task of argument clustering, which aims to acquire frame element knowledge, and propose a method that applies deep metric learning. In this method, a pre-trained language model is fine-tuned to be suitable for distinguishing frame element roles through the use of frame-annotated data, and argument clustering is performed with embeddings obtained from the fine-tuned model. Experimental results on FrameNet demonstrate that our method achieves substantially better performance than existing methods.
Anthology ID:
2023.findings-acl.596
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9356–9364
Language:
URL:
https://aclanthology.org/2023.findings-acl.596
DOI:
10.18653/v1/2023.findings-acl.596
Bibkey:
Cite (ACL):
Kosuke Yamada, Ryohei Sasano, and Koichi Takeda. 2023. Acquiring Frame Element Knowledge with Deep Metric Learning for Semantic Frame Induction. In Findings of the Association for Computational Linguistics: ACL 2023, pages 9356–9364, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Acquiring Frame Element Knowledge with Deep Metric Learning for Semantic Frame Induction (Yamada et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.596.pdf
Video:
 https://aclanthology.org/2023.findings-acl.596.mp4