Existing solutions to zero-shot text classification either conduct prompting with pre-trained language models, which is sensitive to the choices of templates, or rely on large-scale annotated data of relevant tasks for meta-tuning. In this work, we propose a new paradigm based on self-supervised learning to solve zero-shot text classification tasks by tuning the language models with unlabeled data, called self-supervised tuning. By exploring the inherent structure of free texts, we propose a new learning objective called first sentence prediction to bridge the gap between unlabeled data and text classification tasks. After tuning the model to learn to predict the first sentence in a paragraph based on the rest, the model is able to conduct zero-shot inference on unseen tasks such as topic classification and sentiment analysis. Experimental results show that our model outperforms the state-of-the-art baselines on 7 out of 10 tasks. Moreover, the analysis reveals that our model is less sensitive to the prompt design. Our code and pre-trained models are publicly available at https://github.com/DAMO-NLP-SG/SSTuning .

翻译：现有的零样本文本分类解决方案要么使用预训练语言模型进行提示学习，但对模板选择高度敏感；要么依赖大规模标注数据完成相关任务的元调优。本文提出一种基于自监督学习的新范式——自监督调优，通过无标注数据对语言模型进行调优来解决零样本文本分类任务。通过探索自由文本的内在结构，我们提出名为"首句预测"的新学习目标，旨在弥合无标注数据与文本分类任务之间的差距。当模型经调优学会根据段落其余内容预测首句后，即可对主题分类、情感分析等未见任务进行零样本推理。实验结果表明，我们的模型在10个任务中的7个上超越了当前最优基线模型。此外，分析表明该模型对提示模板设计具有更低敏感性。我们的代码与预训练模型已在 https://github.com/DAMO-NLP-SG/SSTuning 公开。