Improving Domain-Generalized Few-Shot Text Classification with Multi-Level Distributional Signatures

Improving Domain-Generalized Few-Shot Text Classification with Multi-Level Distributional Signatures

Domain-generalized few-shot text classification (DG-FSTC) is a new setting for few-shot text classification (FSTC). In DG-FSTC, the model is meta-trained on a multi-domain dataset, and meta-tested on unseen datasets with different domains. However, previous methods mostly construct semantic represen...

Full description

Bibliographic Details
Main Authors: Xuyang Wang, Yajun Du, Danroujing Chen, Xianyong Li, Xiaoliang Chen, Yongquan Fan, Chunzhi Xie, Yanli Li, Jia Liu
Format: Article
Language:English
Published: MDPI AG 2023-01-01
Series:Applied Sciences
Subjects:
domain-generalized few-shot learning
text classification
distributional signature
meta-learning
Online Access:https://www.mdpi.com/2076-3417/13/2/1202

Internet

https://www.mdpi.com/2076-3417/13/2/1202

Similar Items