ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification

56Citations
Citations of this article
39Readers
Mendeley users who have this article in their library.

Abstract

Few-shot text classification has recently been promoted by the meta-learning paradigm which aims to identify target classes with knowledge transferred from source classes with sets of small tasks named episodes. Despite their success, existing works building their meta-learner based on Prototypical Networks are unsatisfactory in learning discriminative text representations between similar classes, which may lead to contradictions during label prediction. In addition, the tasklevel and instance-level overfitting problems in few-shot text classification caused by a few training examples are not sufficiently tackled. In this work, we propose a contrastive learning framework named ContrastNet to tackle both discriminative representation and overfitting problems in few-shot text classification. ContrastNet learns to pull closer text representations belonging to the same class and push away text representations belonging to different classes, while simultaneously introducing unsupervised contrastive regularization at both task-level and instance-level to prevent overfitting. Experiments on 8 few-shot text classification datasets show that ContrastNet outperforms the current state-of-the-art models.

Cite

CITATION STYLE

APA

Chen, J., Zhang, R., Mao, Y., & Xu, J. (2022). ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification. In Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022 (Vol. 36, pp. 10492–10500). Association for the Advancement of Artificial Intelligence. https://doi.org/10.1609/aaai.v36i10.21292

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free