JSAI2023

Presentation information

General Session

General Session » GS-5 Language media processing

[3A1-GS-6] Language media processing

Thu. Jun 8, 2023 9:00 AM - 10:40 AM Room A (Main hall)

座長:是枝 祐太(日立製作所) [現地]

9:00 AM - 9:20 AM

[3A1-GS-6-01] Acquiring Frame Element Knowledge with Deep Metric Learning for Semantic Frame Induction

〇Kosuke Yamada1, Ryohei Sasano1,2, Koichi Takeda1 (1. Nagoya University, 2. RIKEN)

Keywords:semantic frame, deep metric learning, frame element knowledge

For semantic frame induction, words must be grouped according to the frames that they evoke, and their arguments must also be grouped according to the frame element roles that they fill. In this paper, we address the latter task of argument clustering to acquire frame element knowledge, and we 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 based on embeddings obtained from the fine-tuned model. Experimental results on FrameNet demonstrate that our method achieves substantially better performance than existing methods.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.

Password