.png){kind=icon}
返回
Uncertainty quantification for multilabel text classification
.png){kind=icon}
PRE
AI
DOI：10.1002/widm.1384.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep neural networks have recently achieved impressive performance on multilabel text classification. However, the uncertainty in multilabel text classification tasks and their application in the model are often overlooked. To better understand and evaluate the uncertainty in multilabel text classification tasks, we propose a general framework called Uncertainty Quantification for Multilabel Text Classification framework. Based on the prediction results produced by traditional neural networks, the aleatory uncertainty of each classification label and the epistemic uncertainty of the prediction result can further be obtained by this framework. We design experiments to characterize the properties of aleatory uncertainty and epistemic uncertainty from the data characteristics and model features. The experimental results show that this framework is reasonable. Furthermore, we demonstrate how this framework allows us to define the model optimization criterion to identify policies that balance the expected training cost, model performance, and uncertainty sensitivity. This article is categorized under: Algorithmic Development > Bayesian Models
Keyword:
aleatory uncertainty
Bayesian neural network
epistemic uncertainty
multilabel text classification
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:
11.7
论文数:
546
被引数:
5.3K
机构
引用论文
Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learning.png)
CHEMICAL SCIENCE
OAAI
CHEMICAL SCIENCEIF7.4
OAAI分享收藏Dietary butyrate suppresses inflammation through modulating gut microbiota in high-fat diet-fed mice
PREAI
分享收藏Minimum Frequency and Voltage Stability Constrained Unit Commitment for AC/DC Transmission SystemsOAAI
OAAI分享收藏
查看更多内容