CLAIFeb 5, 2023

Meta-Learning Siamese Network for Few-Shot Text Classification

Peking U
arXiv:2302.03507v29 citationsh-index: 43Has Code
Originality Incremental advance
AI Analysis

This work addresses few-shot text classification for domains with limited labeled data, representing an incremental improvement over existing meta-learning methods.

The paper tackled the problem of label scarcity in text classification by proposing Meta-SN, a meta-learning Siamese network that addresses issues in prototypical networks, such as randomness in support sets and ignoring sample importance, resulting in clear superiority over state-of-the-art models on six benchmark datasets.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes