Text classification aims to effectively categorize documents into pre-defined categories. Traditional methods for text classification often rely on large amounts of manually annotated training data, making the process time-consuming and labor-intensive. To address this issue, recent studies have focused on weakly-supervised and extremely weakly-supervised settings, which require minimal or no human annotation, respectively. In previous methods of weakly supervised text classification, pseudo-training data is generated by assigning pseudo-labels to documents based on their alignment (e.g., keyword matching) with specific classes. However, these methods ignore the importance of incorporating the explanations of the generated pseudo-labels, or saliency of individual words, as additional guidance during the text classification training process. To address this limitation, we propose XAI-CLASS, a novel explanation-enhanced extremely weakly-supervised text classification method that incorporates word saliency prediction as an auxiliary task. XAI-CLASS begins by employing a multi-round question-answering process to generate pseudo-training data that promotes the mutual enhancement of class labels and corresponding explanation word generation. This pseudo-training data is then used to train a multi-task framework that simultaneously learns both text classification and word saliency prediction. Extensive experiments on several weakly-supervised text classification datasets show that XAI-CLASS outperforms other weakly-supervised text classification methods significantly. Moreover, experiments demonstrate that XAI-CLASS enhances both model performance and explainability.
翻译:文本分类旨在将文档有效归类至预设类别。传统方法通常依赖大量人工标注的训练数据,导致流程耗时费力。为解决此问题,近年研究聚焦于弱监督与极弱监督场景,这两种方法分别需要极少或无人工标注。在先前的弱监督文本分类方法中,通过基于文档与特定类别的对齐程度(如关键词匹配)赋予伪标签来生成伪训练数据。然而,这些方法忽略了在文本分类训练过程中融入生成伪标签的解释信息(即单词显著性)作为额外指导的重要性。为克服此局限,我们提出XAI-CLASS——一种新颖的基于解释增强的极弱监督文本分类方法,将单词显著性预测作为辅助任务。XAI-CLASS首先通过多轮问答过程生成伪训练数据,该数据促进类别标签与对应解释性单词的相互增强。随后利用此伪训练数据训练一个同时学习文本分类与单词显著性预测的多任务框架。在多个弱监督文本分类数据集上的大量实验表明,XAI-CLASS显著优于其他弱监督文本分类方法。此外,实验证明XAI-CLASS同时提升了模型性能与可解释性。