Textual label names (descriptions) are typically semantically rich in many natural language understanding (NLU) tasks. In this paper, we incorporate the prompting methodology, which is widely used to enrich model input, into the label side for the first time. Specifically, we propose a Mask Matching method, which equips an input with a prompt and its label with another, and then makes predictions by matching their mask representations. We evaluate our method extensively on 8 NLU tasks with 14 datasets. The experimental results show that Mask Matching significantly outperforms its counterparts of fine-tuning and conventional prompt-tuning, setting up state-of-the-art performances in several datasets. Mask Matching is particularly good at handling NLU tasks with large label counts and informative label names. As pioneering efforts that investigate the label-side prompt, we also discuss open issues for future study.

翻译：文本标签名称（描述）在许多自然语言理解（NLU）任务中通常具有丰富的语义。本文首次将广泛用于丰富模型输入的提示方法论引入标签侧。具体而言，我们提出一种掩码匹配方法，该方法为输入配备一个提示，为其标签配备另一个提示，然后通过匹配二者的掩码表示进行预测。我们在涵盖14个数据集的8项NLU任务上对方法进行了广泛评估。实验结果表明，掩码匹配方法在性能上显著优于微调和传统提示调优方法，并在多个数据集上取得了最先进的结果。该方法尤其擅长处理标签数量大且标签名称信息丰富的NLU任务。作为探究标签侧提示的开创性工作，本文还讨论了未来研究的开放性问题。