BriefGPT.xyz
Sep, 2020
弱监督学习的约束标注
Constrained Labeling for Weakly Supervised Learning
HTML
PDF
Chidubem Arachie, Bert Huang
TL;DR
本文提出了一种基于约束空间的弱监督学习方法,将不同的弱监督信号结合起来进行训练,在文本分类和图像分类任务中优于其他方法。
Abstract
Curation of large fully supervised datasets has become one of the major roadblocks for machine learning.
weak supervision
provides an alternative to supervised learning by training with cheap, noisy, and possibly correlated
→