Home
This Title All WIREs
WIREs RSS Feed
How to cite this WIREs title:
WIREs Data Mining Knowl Discov
Impact Factor: 4.476

Uncertainty quantification for multilabel text classification

Full article on Wiley Online Library:   HTML PDF

Can't access this content? Tell your librarian.

Abstract 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
Architecture of the UQ‐MLTC framework
[ Normal View | Magnified View ]
Two cases prediction probability frequency distribution in different datasets. (a) Experiment on two cases of 21578 with different train size. (b) Experiment on two cases of 21578 with different feature dimensions. (c) Experiment on two cases of AAPD with different train size. (d) Experiment on two cases of AAPD with different feature dimensions
[ Normal View | Magnified View ]

Browse by Topic

Algorithmic Development > Bayesian Models

Access to this WIREs title is by subscription only.

Recommend to Your
Librarian Now!

The latest WIREs articles in your inbox

Sign Up for Article Alerts