FZeroTC: fully zero-shot text classification for simultaneously discovering and labeling unseen classes

doi:10.1007/s10115-025-02379-5

	FZeroTC: fully zero-shot text classification for simultaneously discovering and labeling unseen classes
	Duan, Dongsheng 1; Lv, Cunchi 2,3; Zhang, Cheng 2; Hou, Wei 1; Shi, Lei 1; Li, Yangxi 1; Zhao, Xiaofang 2,3
	2025-04-21
发表期刊	KNOWLEDGE AND INFORMATION SYSTEMS
ISSN	0219-1377
页码	25
摘要	With the explosive data growth on the web, there are massive textual data without class labels such that zero-shot text classification has attracted much research attention. However, existing zero-shot text classification models still take the class labels as the weakly supervised signal, which are usually unavailable in the open domain. In this paper, we study the text classification problem in a fully zero-shot setting, in which not only are we not given any training samples for unseen classes, but also the label names and the total number of unseen classes are unknown. We propose a fully zero-shot text classification model (FZeroTC) in a semi-supervised learning framework to simultaneously discover and label unseen classes. In the FZeroTC model, a pairwise loss and a Kullback-Leibler divergence-based regularization term are specially designed for unseen class discovery, and a faraway loss is specially designed for class labeling. We propose three different kinds of learning strategies based on the pretrained language model and prompt learning to train FZeroTC. From extensive experiments on four public text classification datasets, FZeroTC outperforms the state-of-the-art zero-shot text classification models in terms of unseen class discovery performance and can provide high-quality labels for unseen classes.
关键词	Zero-shot text classification Semi-supervised learning Pretrained language model Prompt learning Class discovery Class labeling
DOI	10.1007/s10115-025-02379-5
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62272125] ; National Natural Science Foundation of China[62192785]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Information Systems
WOS记录号	WOS:001471214800001
出版者	SPRINGER LONDON LTD
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/40603
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Duan, Dongsheng; Zhang, Cheng
作者单位	1.Coordinat Ctr China, Natl Comp Network Emergency Response Tech Team, Beijing 100029, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Duan, Dongsheng,Lv, Cunchi,Zhang, Cheng,et al. FZeroTC: fully zero-shot text classification for simultaneously discovering and labeling unseen classes[J]. KNOWLEDGE AND INFORMATION SYSTEMS,2025:25.
APA	Duan, Dongsheng.,Lv, Cunchi.,Zhang, Cheng.,Hou, Wei.,Shi, Lei.,...&Zhao, Xiaofang.(2025).FZeroTC: fully zero-shot text classification for simultaneously discovering and labeling unseen classes.KNOWLEDGE AND INFORMATION SYSTEMS,25.
MLA	Duan, Dongsheng,et al."FZeroTC: fully zero-shot text classification for simultaneously discovering and labeling unseen classes".KNOWLEDGE AND INFORMATION SYSTEMS (2025):25.