Disentangling Task Relations for Few-shot Text Classification via Self-Supervised Hierarchical Task Clustering
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.
National Natural Science Foundation of China;
|Document Type||Conference paper|
|Department||Southern University of Science and Technology|
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
|Corresponding Author Affilication||Southern University of Science and Technology|
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.
|Files in This Item:||There are no files associated with this item.|
|Recommend this item|
|Export to Endnote|
|Export to Excel|
|Export to Csv|
|Similar articles in Google Scholar|
|Similar articles in Baidu Scholar|
|Similar articles in Bing Scholar|
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.