STT: Soft Template Tuning for Few-Shot Adaptation
STT: Soft Template Tuning for Few-Shot Adaptation
复制标题
DOI：
10.1109/icdmw58026.2022.00122
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Ping Yu;Wei Wang-;Chunyuan Li;Ruiyi Zhang;Zhanpeng Jin;Changyou Chen
中科院分区：
文献类型：
--
作者：
Ping Yu;Wei Wang-;Chunyuan Li;Ruiyi Zhang;Zhanpeng Jin;Changyou Chen
快速调优是一种非常有效的工具，可以将预先训练好的模型适应下游任务。然而，标准的基于任务的方法主要考虑下游任务有足够数据的情况。目前还不清楚这种优势是否可以转移到少数拍摄制度，其中只有有限的数据可用于每个下游任务。虽然一些工作已经证明了在少数镜头设置下的快速调谐的潜力，但是通过搜索离散提示或在有限数据下调谐软提示的主流方法仍然非常具有挑战性。通过大量的实证研究，我们发现，在快速调整和完全微调之间仍然存在着差距。为了弥合差距，我们提出了一个新的模板调整框架，称为软模板调整（STT）1。STT结合了手动和自动提示，并将下游分类任务视为掩码语言建模任务。对不同设置的综合评价表明，STT可以在不引入额外参数的情况下缩小微调和基于自适应的方法之间的差距。值得注意的是，它甚至可以在情感分类任务上优于耗时和资源消耗的微调方法。
Prompt tuning has been an extremely effective tool to adapt a pre-trained model to downstream tasks. However, standard prompt-based methods mainly consider the case of sufficient data of downstream tasks. It is still unclear whether the advantage can be transferred to the few-shot regime, where only limited data are available for each downstream task. Although some works have demonstrated the potential of prompt-tuning under the few-shot setting, the main stream methods via searching discrete prompts or tuning soft prompts with limited data are still very challenging. Through extensive empirical studies, we find that there is still a gap between prompt tuning and fully fine-tuning for few-shot learning. To bridge the gap, we propose a new prompt-tuning framework, called Soft Template Tuning (STT) 1. STT combines manual and auto prompts, and treats down-stream classification tasks as a masked language modeling task. Comprehensive evaluation on different settings suggests STT can close the gap between fine-tuning and prompt-based methods without introducing additional parameters. Significantly, it can even outperform the time- and resource-consuming fine-tuning method on sentiment classification tasks.