BriefGPT.xyz
Oct, 2022
利用标签提示弃权改进少样本关系抽取
Better Few-Shot Relation Extraction with Label Prompt Dropout
HTML
PDF
Peiyuan Zhang, Wei Lu
TL;DR
该论文研究了如何利用有限的样本进行关系提取，并建议使用新的标签提示现象(即随机地去掉标签描述)来提高类别表征，以在少样本学习任务中获得更好的结果。
Abstract
Few-shot
relation extraction
aims to learn to identify the relation between two entities based on very limited training examples. Recent efforts found that
textual labels
(i.e., relation names and relation descri
→