Pretrained language models (PLMs) have demonstrated remarkable performance in various natural language processing tasks: Unidirectional PLMs (e.g., GPT) are well known for their superior text generation capabilities; bidirectional PLMs (e.g., BERT) have been the prominent choice for natural language understanding (NLU) tasks. While both types of models have achieved promising few-shot learning performance, their potential for zero-shot learning has been underexplored. In this paper, we present a simple approach that uses both types of PLMs for fully zero-shot learning of NLU tasks without requiring any task-specific data: A unidirectional PLM generates class-conditioned texts guided by prompts, which are used as the training data for fine-tuning a bidirectional PLM. With quality training data selected based on the generation probability and regularization techniques (label smoothing and temporal ensembling) applied to the fine-tuning stage for better generalization and stability, our approach demonstrates strong performance across seven classification tasks of the GLUE benchmark (e.g., 72.3/73.8 on MNLI-m/mm and 92.8 on SST-2), significantly outperforming zero-shot prompting methods and achieving even comparable results to strong few-shot approaches using 32 training samples per class.

本文提出了一种简单的方法，使用预训练语言模型 (Pretrained language models) 进行全零样本学习 (zero-shot learning) 自然语言理解任务 (NLU tasks)。该方法使用单向和双向 PLMs 生成和训练数据，其中训练数据是使用提示 (prompts) 引导的类别条件文本。使用这种方法，在 GLUE 数据集的七个分类任务中取得了强劲的表现 (例如在 MNLI-m/mm 上的 72.3/73.8，以及在 SST-2 上的 92.8)，相对于零样本提示方法，甚至实现了与使用每类 32 个训练样本的强有力的少样本方法相当的结果。同时，采用了标签平滑和时间模型的融合技术以达到更好的泛化和稳定性。

利用语言模型生成训练数据：走向零样本语言理解