Few-shot learning has been used to tackle the problem of label scarcity in text classification, of which meta-learning based methods have shown to be effective, such as the prototypical networks (PROTO). Despite the success of PROTO, there still exist three main problems: (1) ignore the randomness of the sampled support sets when computing prototype vectors; (2) disregard the importance of labeled samples; (3) construct meta-tasks in a purely random manner. In this paper, we propose a Meta-Learning Siamese Network, namely, Meta-SN, to address these issues. Specifically, instead of computing prototype vectors from the sampled support sets, Meta-SN utilizes external knowledge (e.g. class names and descriptive texts) for class labels, which is encoded as the low-dimensional embeddings of prototype vectors. In addition, Meta-SN presents a novel sampling strategy for constructing meta-tasks, which gives higher sampling probabilities to hard-to-classify samples. Extensive experiments are conducted on six benchmark datasets to show the clear superiority of Meta-SN over other state-of-the-art models. For reproducibility, all the datasets and codes are provided at https://github.com/hccngu/Meta-SN.

翻译：少样本学习已被用于解决文本分类中的标签稀缺问题，其中基于元学习的方法（如原型网络PROTO）已被证明是有效的。尽管PROTO取得了成功，但仍存在三个主要问题：(1) 计算原型向量时忽略了采样支持集的随机性；(2) 未考虑标记样本的重要性；(3) 以纯随机方式构建元任务。本文提出一种元学习孪生网络（Meta-SN）来解决这些问题。具体而言，Meta-SN不再从采样的支持集中计算原型向量，而是利用类别标签的外部知识（如类别名称和描述文本），将其编码为原型向量的低维嵌入。此外，Meta-SN提出了一种新的元任务构建采样策略，为难以分类的样本赋予更高的采样概率。在六个基准数据集上进行的大量实验表明，Meta-SN显著优于其他最先进模型。为便于复现，所有数据集和代码均提供于https://github.com/hccngu/Meta-SN。