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

Zha，Juan1; Li，Zheng2; Wei，Ying3; Zhang，Yu4

2022

Findings of the Association for Computational Linguistics: EMNLP 2022

5265-5276

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.

Corresponding

English

National Natural Science Foundation of China[62076118];

2-s2.0-85140740164

Scopus

1.University of Southern California,United States
2.Amazon.com Inc,United States
3.City University of Hong Kong,Hong Kong
4.Southern University of Science and Technology,China

Zha，Juan,Li，Zheng,Wei，Ying,et al. Disentangling Task Relations for Few-shot Text Classification via Self-Supervised Hierarchical Task Clustering[C],2022:5265-5276.