BriefGPT.xyz
Jan, 2021
通过噪声建模实现文本分类标签噪声的鲁棒性
Towards Robustness to Label Noise in Text Classification via Noise Modeling
HTML
PDF
Siddhant Garg, Goutham Ramakrishnan, Varun Thumbe
TL;DR
该论文研究了NLP中文本分类的标签噪声问题，提出了一种基于beta混合模型的辅助噪声模型，通过此模型可以减轻标签噪声对分类器的影响，提高分类准确率并防止过度拟合。
Abstract
Large datasets in
nlp
suffer from noisy labels, due to erroneous automatic and human annotation procedures. We study the problem of
text classification
with
→