Mitigating Uncertainty in Document Classification
This addresses the need for more accurate uncertainty-aware classifiers in applications like medical diagnosis, where human resources are limited, though it appears incremental as it builds on existing dropout-based methods.
The paper tackled the problem of improving overall prediction accuracy in document classification by mitigating uncertainty, particularly when human experts handle uncertain predictions. It achieved an accuracy improvement from 0.78 to 0.92 on the 20NewsGroup dataset when 30% of uncertain predictions were referred to humans.
The uncertainty measurement of classifiers' predictions is especially important in applications such as medical diagnoses that need to ensure limited human resources can focus on the most uncertain predictions returned by machine learning models. However, few existing uncertainty models attempt to improve overall prediction accuracy where human resources are involved in the text classification task. In this paper, we propose a novel neural-network-based model that applies a new dropout-entropy method for uncertainty measurement. We also design a metric learning method on feature representations, which can boost the performance of dropout-based uncertainty methods with smaller prediction variance in accurate prediction trials. Extensive experiments on real-world data sets demonstrate that our method can achieve a considerable improvement in overall prediction accuracy compared to existing approaches. In particular, our model improved the accuracy from 0.78 to 0.92 when 30\% of the most uncertain predictions were handed over to human experts in "20NewsGroup" data.