English

Meta-Learning Siamese Network for Few-Shot Text Classification

Computation and Language 2023-03-17 v2 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.2302.03507,
  title  = {Meta-Learning Siamese Network for Few-Shot Text Classification},
  author = {Chengcheng Han and Yuhe Wang and Yingnan Fu and Xiang Li and Minghui Qiu and Ming Gao and Aoying Zhou},
  journal= {arXiv preprint arXiv:2302.03507},
  year   = {2023}
}
R2 v1 2026-06-28T08:34:11.366Z