论文标题
不要提示，搜索！使用语言模型的基于采矿的零拍学习
Don't Prompt, Search! Mining-based Zero-Shot Learning with Language Models
论文作者
论文摘要
像Bert这样的蒙版语言模型可以通过重新设计下游任务作为文本填充来执行零拍情况的文本分类。但是，这种方法对用于提示模型的模板高度敏感，但是在严格的零拍设置中设计它们时，从业者则是盲目的。在本文中，我们提出了一种基于零射学习的替代性采矿方法。我们不用提示语言模型，而是使用正则表达式来挖掘未标记的Corpora标记的示例，这些示例可以通过提示进行过滤，并用于验证预验证的模型。我们的方法比提示更灵活，更容易解释，并且在使用可比模板时，在各种任务上都表现出色。我们的结果表明，提示的成功可以部分解释，该模型在训练过程中暴露于类似示例的模型可以通过正则表达式直接检索。
Masked language models like BERT can perform text classification in a zero-shot fashion by reformulating downstream tasks as text infilling. However, this approach is highly sensitive to the template used to prompt the model, yet practitioners are blind when designing them in strict zero-shot settings. In this paper, we propose an alternative mining-based approach for zero-shot learning. Instead of prompting language models, we use regular expressions to mine labeled examples from unlabeled corpora, which can optionally be filtered through prompting, and used to finetune a pretrained model. Our method is more flexible and interpretable than prompting, and outperforms it on a wide range of tasks when using comparable templates. Our results suggest that the success of prompting can partly be explained by the model being exposed to similar examples during pretraining, which can be directly retrieved through regular expressions.
