文献类型：期刊文献

英文题名：CPCL: Conceptual prototypical contrastive learning for Few-Shot text classification

作者：Cheng, Tao[1];Cheng, Hua[1];Fang, Yiquan[1];Liu, Yufei[1];Gao, Caiting[1]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China

年份：2023

卷号：45

期号：6

起止页码：11963

外文期刊名：JOURNAL OF INTELLIGENT & FUZZY SYSTEMS

收录：;EI(收录号：20235015227322);WOS:【SCI-EXPANDED(收录号:WOS:001120921100171)】；

语种：英文

外文关键词：Prototypical network; text classification; Few-Shot learning; prompt learning

摘要：As prototype-based Few-Shot Learning methods, Prototypical Network generates prototypes for each class in a low-resource state and classify by a metric module. Therefore, the quality of prototypes matters but they are inaccurate from the few support instances, and the domain-specific information of training data are harmful to the generalizability of prototypes. We propose a Conceptual Prototype (CP), which contains both rich instance and concept features. The numerous query data can inspire the few support instances. An interactive network is designed to leverage the interrelation between support set and query-detached set to acquire a rich Instance Prototype which is typical on the whole data. Besides, class labels are introduced to prototype by prompt engineering, which makes it more conceptual. The label-only concept makes prototype immune to domain-specific information in training phase to improve its generalizability. Based on CP, Conceptual Prototypical Contrastive Learning (CPCL) is proposed where PCL brings instances closer to its corresponding prototype and pushes away from other prototypes. "2-way 5-shot" experiments show that CPCL achieves 92.41% accuracy on ARSC dataset, 2.30% higher than other prototype-based models. Meanwhile, the 0-shot performance of CPCL is comparable to Induction Network in the 5-shot way, indicating that our model is adequate for 0-shot tasks.