RulePrompt: Weakly Supervised Text Classification with Prompting PLMs and Self-Iterative Logical Rules
Miaomiao Li, Jiaqi Zhu, Yang Wang, Yi Yang, Yilin Li, Hongan Wang
TL;DR
RulePrompt tackles weakly supervised text classification by pairing prompting PLMs with automatically mined, disjunctive normal form category rules. It builds a self-iterative loop where pseudo labels and category rules mutually refine each other, aided by a self-supervised fine-tuning stage. The approach uses three PLM-based perspectives—verbalizer expansion, embedding-based similarity, and word overlap—to generate robust pseudo labels from the evolving rules. Empirical results across four datasets show state-of-the-art performance among weakly supervised methods and strong interpretability of the learned category rules. The work advances practical WSTC by fusing symbolic rule representations with neural prompting in a corpus-adaptive, iteratively optimized framework.
Abstract
Weakly supervised text classification (WSTC), also called zero-shot or dataless text classification, has attracted increasing attention due to its applicability in classifying a mass of texts within the dynamic and open Web environment, since it requires only a limited set of seed words (label names) for each category instead of labeled data. With the help of recently popular prompting Pre-trained Language Models (PLMs), many studies leveraged manually crafted and/or automatically identified verbalizers to estimate the likelihood of categories, but they failed to differentiate the effects of these category-indicative words, let alone capture their correlations and realize adaptive adjustments according to the unlabeled corpus. In this paper, in order to let the PLM effectively understand each category, we at first propose a novel form of rule-based knowledge using logical expressions to characterize the meanings of categories. Then, we develop a prompting PLM-based approach named RulePrompt for the WSTC task, consisting of a rule mining module and a rule-enhanced pseudo label generation module, plus a self-supervised fine-tuning module to make the PLM align with this task. Within this framework, the inaccurate pseudo labels assigned to texts and the imprecise logical rules associated with categories mutually enhance each other in an alternative manner. That establishes a self-iterative closed loop of knowledge (rule) acquisition and utilization, with seed words serving as the starting point. Extensive experiments validate the effectiveness and robustness of our approach, which markedly outperforms state-of-the-art weakly supervised methods. What is more, our approach yields interpretable category rules, proving its advantage in disambiguating easily-confused categories.