Few-shot Text Classification with Distributional Signatures

TL;DR

This paper introduces a meta-learning approach for few-shot text classification that utilizes distributional signatures of words to improve transferability and outperforms existing methods across multiple benchmarks.

Contribution

The paper proposes a novel method combining distributional signatures with meta-learning to enhance few-shot text classification performance.

Findings

Outperforms prototypical networks by 20% on average in 1-shot classification

Effective across six benchmark datasets

Leverages word distributional signatures for better transferability

Abstract

In this paper, we explore meta-learning for few-shot text classification. Meta-learning has shown strong performance in computer vision, where low-level patterns are transferable across learning tasks. However, directly applying this approach to text is challenging--lexical features highly informative for one task may be insignificant for another. Thus, rather than learning solely from words, our model also leverages their distributional signatures, which encode pertinent word occurrence patterns. Our model is trained within a meta-learning framework to map these signatures into attention scores, which are then used to weight the lexical representations of words. We demonstrate that our model consistently outperforms prototypical networks learned on lexical knowledge (Snell et al., 2017) in both few-shot text classification and relation classification by a significant margin across six benchmark datasets (20.0% on average in 1-shot classification).