Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification

Abstract

Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieved state-of-the-art performance. However, existing solutions heavily rely on the exploitation of lexical features and their distributional signatures on training data, while neglecting to strengthen the model's ability to adapt to new tasks. In this paper, we propose a novel meta-learning framework integrated with an adversarial domain adaptation network, aiming to improve the adaptive ability of the model and generate high-quality text embedding for new classes. Extensive experiments are conducted on four benchmark datasets and our method demonstrates clear superiority over the state-of-the-art models in all the datasets. In particular, the accuracy of 1shot and 5-shot classification on the dataset of 20 Newsgroups is boosted from 52.1% to 59.6%, and from 68.3% to 77.8%, respectively 1 .

REKP: Refined External Knowledge into Prompt-Tuning for Few-Shot Text Classification

“…Processing text classification problems with a small number of labeled samples is the topic of few-shot text classification. The primary objective is to enhance the generalization capability of pre-trained models for rapid adaptation to new tasks [12][13][14] while acquiring sufficient prior knowledge. The three prevailing techniques employed for few-shot text categorization include data augmentation, transfer learning, and meta-learning.…”