Disentangling Task Relations for Few-shot Text Classification via Self-Supervised Hierarchical Task Clustering

TL;DR

This paper introduces a self-supervised hierarchical task clustering method to improve few-shot text classification by organizing diverse tasks into clusters and explicitly capturing task relations, enhancing adaptability and interpretability.

Contribution

The paper proposes a novel SS-HTC approach that dynamically clusters heterogeneous tasks and disentangles task relations for better few-shot text classification.

Findings

SS-HTC outperforms existing methods on five benchmarks.

Hierarchical clustering improves task organization and transferability.

Explicit relation modeling enhances interpretability.

Abstract

Few-Shot Text Classification (FSTC) imitates humans to learn a new text classifier efficiently with only few examples, by leveraging prior knowledge from historical tasks. However, most prior works assume that all the tasks are sampled from a single data source, which cannot adapt to real-world scenarios where tasks are heterogeneous and lie in different distributions. As such, existing methods may suffer from their globally knowledge-shared mechanisms to handle the task heterogeneity. On the other hand, inherent task relation are not explicitly captured, making task knowledge unorganized and hard to transfer to new tasks. Thus, we explore a new FSTC setting where tasks can come from a diverse range of data sources. To address the task heterogeneity, we propose a self-supervised hierarchical task clustering (SS-HTC) method. SS-HTC not only customizes cluster-specific knowledge by dynamically organizing heterogeneous tasks into different clusters in hierarchical levels but also disentangles underlying relations between tasks to improve the interpretability. Extensive experiments on five public FSTC benchmark datasets demonstrate the effectiveness of SS-HTC.