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 1-shot 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.

本文提出了一种新的元学习框架，集成对抗域适应网络，旨在提高模型的适应能力并为新类别生成高质量的文本嵌入。在四个基准数据集上进行了大量实验，结果表明我们的方法在所有数据集上都明显优于现有技术，特别是在 20 个新闻组数据集上，1-shot 和 5-shot 分类的准确性从 52.1％提高到 59.6％和从 68.3％提高到 77.8％。