.png){kind=icon}
返回
Learning label smoothing for text classification
.png){kind=icon}
OA
AI
DOI：10.7717/peerj-cs.2005.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Training with soft labels instead of hard labels can effectively improve the robustness and generalization of deep learning models. Label smoothing often provides uniformly distributed soft labels during the training process, whereas it does not take the semantic difference of labels into account. This article introduces discriminationaware label smoothing, an adaptive label smoothing approach that learns appropriate distributions of labels for iterative optimization objectives. In this approach, positive and negative samples are employed to provide experience from both sides, and the performances of regularization and model calibration are improved through an iterative learning method. Experiments on five text classification datasets demonstrate the effectiveness of the proposed method.
Keyword:
Text classi fi cation
Neural network
Label smoothing
Excessive regularization
Soft label
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
2.5
论文数:
3.4K
被引数:
6.9K
机构
引用论文
分享收藏Femtosecond Charge Transfer Dynamics of a Modified DNA Base: 2-Aminopurine in Complexes with Nucleotides.png)
ChemPhysChemOAAI
ChemPhysChemIF0
OAAI分享收藏Cobalt and Copper Composite Oxides as Efficient Catalysts for Preferential Oxidation of CO in H2-Rich Stream钴和铜复合氧化物作为H2-Rich流中CO优先氧化的有效催化剂
PREAI
分享收藏分享收藏
查看更多内容