足够好的例子外推
Good-Enough Example Extrapolation
摘要:
本文提出了一个问题,是否外推隐藏的空间分布的文本例子从一个类到另一个是一个有效的归纳偏见数据增强。为了使这个问题可操作化,我提出了一个简单的数据增强协议,称为“足够好的示例外推”(GE 3)。GE3是轻量级的,没有超参数。应用于三个文本分类数据集的各种数据不平衡的情况下,GE3提高性能比上采样和其他隐藏空间数据增强方法。
英文摘要:
This paper asks whether extrapolating the hidden space distribution of text examples from one class onto another is a valid inductive bias for data augmentation. To operationalize this question, I propose a simple data augmentation protocol called "good-enough example extrapolation" (GE3). GE3 is lightweight and has no hyperparameters. Applied to three text classification datasets for various data imbalance scenarios, GE3 improves performance more than upsampling and other hidden-space data augmentation methods.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。