A Chinese Few-Shot Text Classification Method Utilizing Improved Prompt Learning and Unlabeled Data

Insufficiently labeled samples and low-generalization performance have become significant natural language processing problems, drawing significant concern for few-shot text classification (FSTC). Advances in prompt learning have significantly improved the performance of FSTC. However, prompt learni...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Tingkai Hu, Zuqin Chen, Jike Ge, Zhaoxu Yang, Jichao Xu
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2023-03-01
coleção:	Applied Sciences
Assuntos:	Chinese few-shot text classification prompt learning unlabeled data pre-trained language model
Acesso em linha:	https://www.mdpi.com/2076-3417/13/5/3334
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!