Does Head Label Help for Long-Tailed Multi-Label Text Classification

Multi-label text classification (MLTC) aims to annotate documents with the most relevant labels from a number of candidate labels. In real applications, the distribution of label frequency often exhibits a long tail, i. e. , a few labels are associated with a large number of documents (a. k. a. head labels), while a large fraction of labels are associated with a small number of documents (a. k. a. tail labels). To address the challenge of insufficient training data on tail label classification, we propose a Head-to-Tail Network (HTTN) to transfer the meta-knowledge from the data-rich head labels to data-poor tail labels. The meta-knowledge is the mapping from fewshot network parameters to many-shot network parameters, which aims to promote the generalizability of tail classifiers. Extensive experimental results on three benchmark datasets demonstrate that HTTN consistently outperforms the stateof-the-art methods. The code and hyper-parameter settings are released for reproducibility1.

Authors

• Lin Xiao Beijing Jiaotong University
• Xiangliang Zhang University of Notre Dame
• Liping Jing Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, Beijing Jiaotong University
• Chi Huang
• Mingyang Song Tencent Hunyuan

Keywords

No keywords are indexed for this paper.