BriefGPT.xyz
Sep, 2023
检索增强的元学习用于低资源文本分类
Retrieval-Augmented Meta Learning for Low-Resource Text Classification
HTML
PDF
Rongsheng Li, Yangning Li, Yinghui Li, Chaiyut Luoyiching, Hai-Tao Zheng...
TL;DR
基于检索增强元学习 (RAML) 的元学习方法,通过从外部语料库中检索非参数性知识以进行推理,以解决元学习场景中缺乏多样化训练数据导致的泛化性能差的问题,并在低资源文本分类任务中显著优于当前最优模型。
Abstract
meta learning
have achieved promising performance in
low-resource text classification
which aims to identify target classes with knowledge transferred from source classes with sets of small tasks named episodes.
→