Adaptive inductive network for few-shot relation extraction

Xiaoming Zhang; Shan Lu

doi:10.1117/12.2631869

14 April 2022 Adaptive inductive network for few-shot relation extraction

Xiaoming Zhang, Shan Lu

Proceedings Volume 12178, International Conference on Signal Processing and Communication Technology (SPCT 2021); 1217815 (2022) https://doi.org/10.1117/12.2631869
Event: International Conference on Signal Processing and Communication Technology (SPCT 2021), 2021, Tianjin, China

Abstract

In this paper, we propose an Adaptive Inductive Network(AINet), whose contributions are mainly manifested in two aspects: First, we propose a routing process evaluation method to reduce noise interference caused by different samples and obtain an accurate representation of the sample class. The second is to introduce a memory iteration mechanism in AINet, which provides a class feature template for the sample induction process to help the model quickly determine the class representation. The experimental results show that AINet can effectively handle the few-shot relationship extraction task, and demonstrate the validity of the class feature modeling method in the few-shot relationship extraction task.

Citation Download Citation

Xiaoming Zhang and Shan Lu "Adaptive inductive network for few-shot relation extraction", Proc. SPIE 12178, International Conference on Signal Processing and Communication Technology (SPCT 2021), 1217815 (14 April 2022); https://doi.org/10.1117/12.2631869

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available