English

Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning

Computation and Language 2021-04-06 v1

Abstract

Exploiting label hierarchies has become a promising approach to tackling the zero-shot multi-label text classification (ZS-MTC) problem. Conventional methods aim to learn a matching model between text and labels, using a graph encoder to incorporate label hierarchies to obtain effective label representations \cite{rios2018few}. More recently, pretrained models like BERT \cite{devlin2018bert} have been used to convert classification tasks into a textual entailment task \cite{yin-etal-2019-benchmarking}. This approach is naturally suitable for the ZS-MTC task. However, pretrained models are underexplored in the existing work because they do not generate individual vector representations for text or labels, making it unintuitive to combine them with conventional graph encoding methods. In this paper, we explore to improve pretrained models with label hierarchies on the ZS-MTC task. We propose a Reinforced Label Hierarchy Reasoning (RLHR) approach to encourage interdependence among labels in the hierarchies during training. Meanwhile, to overcome the weakness of flat predictions, we design a rollback algorithm that can remove logical errors from predictions during inference. Experimental results on three real-life datasets show that our approach achieves better performance and outperforms previous non-pretrained methods on the ZS-MTC task.

Keywords

Cite

@article{arxiv.2104.01666,
  title  = {Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning},
  author = {Hui Liu and Danqing Zhang and Bing Yin and Xiaodan Zhu},
  journal= {arXiv preprint arXiv:2104.01666},
  year   = {2021}
}

Comments

Accepted to Main Conference of NAACL 2021 as Long Paper

R2 v1 2026-06-24T00:50:32.638Z