PIEClass: Weakly-Supervised Text Classification with Prompting and Noise-Robust Iterative Ensemble Training

TL;DR

PIEClass introduces a weakly-supervised text classification method that leverages prompting and iterative ensemble training to improve pseudo label quality and classifier robustness, reducing reliance on human annotations.

Contribution

The paper proposes PIEClass, a novel approach combining zero-shot prompting and noise-robust ensemble training to enhance weakly-supervised text classification.

Findings

Outperforms existing baselines on seven benchmark datasets.

Achieves comparable performance to fully-supervised classifiers on sentiment tasks.

Effectively reduces noise in pseudo labels through iterative training.

Abstract

Weakly-supervised text classification trains a classifier using the label name of each target class as the only supervision, which largely reduces human annotation efforts. Most existing methods first use the label names as static keyword-based features to generate pseudo labels, which are then used for final classifier training. While reasonable, such a commonly adopted framework suffers from two limitations: (1) keywords can have different meanings in different contexts and some text may not have any keyword, so keyword matching can induce noisy and inadequate pseudo labels; (2) the errors made in the pseudo label generation stage will directly propagate to the classifier training stage without a chance of being corrected. In this paper, we propose a new method, PIEClass, consisting of two modules: (1) a pseudo label acquisition module that uses zero-shot prompting of pre-trained language models (PLM) to get pseudo labels based on contextualized text understanding beyond static keyword matching, and (2) a noise-robust iterative ensemble training module that iteratively trains classifiers and updates pseudo labels by utilizing two PLM fine-tuning methods that regularize each other. Extensive experiments show that PIEClass achieves overall better performance than existing strong baselines on seven benchmark datasets and even achieves similar performance to fully-supervised classifiers on sentiment classification tasks.