Yutai Hou, Cheng Chen, Xianzhen Luo, Bohan Li, Wanxiang Che
TL;DR反向提示方法结合迭代预测策略成功提高短语标记任务的效果(在 10 个样本数据集上提高 6.1 个 F1 分数),并实现了新的最先进性能。
Abstract
prompting methods recently achieve impressive success in few-shot learning.
These methods modify input samples with prompt sentence pieces, and decode
label tokens to map samples to corresponding labels. However,