Recently, prompt-based fine-tuning has garnered considerable interest as a core technique for few-shot text classification task. This approach reformulates the fine-tuning objective to align with the Masked Language Modeling (MLM) objective. Leveraging unlabeled data, prompt-based self-training has shown greater effectiveness in binary and three-class classification. However, prompt-based self-training for multi-class classification has not been adequately investigated, despite its significant applicability to real-world scenarios. Moreover, extending current methods to multi-class classification suffers from the verbalizer that extracts the predicted value of manually pre-defined single label word for each class from MLM predictions. Consequently, we introduce a novel, efficient verbalizer structure, named Mapping-free Automatic Verbalizer (MAV). Comprising two fully connected layers, MAV serves as a trainable verbalizer that automatically extracts the requisite word features for classification by capitalizing on all available information from MLM predictions. Experimental results on five multi-class classification datasets indicate MAV's superior self-training efficacy.

翻译：近来，基于提示的微调作为少样本文本分类任务的核心技术引起了广泛关注。该方法重新定义了微调目标，使其与掩码语言建模（MLM）目标相一致。借助未标注数据，基于提示的自训练在二分类和三分类任务中展现出更高的有效性。然而，尽管多类分类在现实场景中具有显著的应用价值，但对此类任务的基于提示的自训练研究尚不充分。此外，将现有方法扩展到多类分类时，受限于动词生成器——该结构从MLM预测中提取每个类别预定义的单个标签词的预测值。为此，我们提出一种新颖且高效的动词生成器结构，称为无映射自动动词生成器（MAV）。MAV由两个全连接层组成，作为可训练动词生成器，通过充分利用MLM预测中的所有可用信息，自动提取分类所需的词特征。在五个多类分类数据集上的实验结果表明，MAV具有优越的自训练效能。