Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

HPT: Hierarchy-aware Prompt Tuning for Hierarchical Text Classification

About

Hierarchical text classification (HTC) is a challenging subtask of multi-label classification due to its complex label hierarchy. Recently, the pretrained language models (PLM)have been widely adopted in HTC through a fine-tuning paradigm. However, in this paradigm, there exists a huge gap between the classification tasks with sophisticated label hierarchy and the masked language model (MLM) pretraining tasks of PLMs and thus the potentials of PLMs can not be fully tapped. To bridge the gap, in this paper, we propose HPT, a Hierarchy-aware Prompt Tuning method to handle HTC from a multi-label MLM perspective. Specifically, we construct a dynamic virtual template and label words that take the form of soft prompts to fuse the label hierarchy knowledge and introduce a zero-bounded multi-label cross entropy loss to harmonize the objectives of HTC and MLM. Extensive experiments show HPT achieves state-of-the-art performances on 3 popular HTC datasets and is adept at handling the imbalance and low resource situations. Our code is available at https://github.com/wzh9969/HPT.

Zihan Wang, Peiyi Wang, Tianyu Liu, Binghuai Lin, Yunbo Cao, Zhifang Sui, Houfeng Wang• 2022

Related benchmarks

TaskDatasetResultRank
Hierarchical Text ClassificationWeb-of-Science (WOS) Depth 2 (test)
Micro-F179.85
25
Hierarchical Text ClassificationRCV1 Depth 4 V2
Micro-F165.73
20
Hierarchical Text ClassificationDBpedia Depth 3
Micro-F196.13
20
Hierarchical Text ClassificationWOS few-shot
Micro-F180.69
20
Hierarchical Text ClassificationWOS full-shot
Micro-F187.1
5
Showing 5 of 5 rows

Other info

Follow for update