Improve Meta-learning for Few-Shot Text Classification with All You Can Acquire from the Tasks

TL;DR

This paper introduces a task-adaptive metric learning approach for few-shot text classification that leverages label information and optimal transport to improve class prototype estimation without external resources.

Contribution

It proposes a novel method using label-guided metric space construction and optimal transport to enhance few-shot text classification performance.

Findings

Outperforms state-of-the-art models on eight benchmark datasets.

Effectively reduces intra-class differences and increases inter-class differences.

Demonstrates robustness without external knowledge or pre-trained models.

Abstract

Meta-learning has emerged as a prominent technology for few-shot text classification and has achieved promising performance. However, existing methods often encounter difficulties in drawing accurate class prototypes from support set samples, primarily due to probable large intra-class differences and small inter-class differences within the task. Recent approaches attempt to incorporate external knowledge or pre-trained language models to augment data, but this requires additional resources and thus does not suit many few-shot scenarios. In this paper, we propose a novel solution to address this issue by adequately leveraging the information within the task itself. Specifically, we utilize label information to construct a task-adaptive metric space, thereby adaptively reducing the intra-class differences and magnifying the inter-class differences. We further employ the optimal transport technique to estimate class prototypes with query set samples together, mitigating the problem of inaccurate and ambiguous support set samples caused by large intra-class differences. We conduct extensive experiments on eight benchmark datasets, and our approach shows obvious advantages over state-of-the-art models across all the tasks on all the datasets. For reproducibility, all the datasets and codes are available at https://github.com/YvoGao/LAQDA.