Deep neural networks have significantly contributed to the success in
predictive accuracy for classification tasks. However, they tend to make
over-confident predictions in real-world settings, where domain shifting and
out-of-distribution (OOD) examples exist. Most research on uncertainty
estimation focuses on computer vision because it provides visual validation on
uncertainty quality. However, few have been presented in the natural language
process domain. Unlike Bayesian methods that indirectly infer uncertainty
through weight uncertainties, current evidential uncertainty-based methods
explicitly model the uncertainty of class probabilities through subjective
opinions. They further consider inherent uncertainty in data with different
root causes, vacuity (i.e., uncertainty due to a lack of evidence) and
dissonance (i.e., uncertainty due to conflicting evidence). In our paper, we
firstly apply evidential uncertainty in OOD detection for text classification
tasks. We propose an inexpensive framework that adopts both auxiliary outliers
and pseudo off-manifold samples to train the model with prior knowledge of a
certain class, which has high vacuity for OOD samples. Extensive empirical
experiments demonstrate that our model based on evidential uncertainty
outperforms other counterparts for detecting OOD examples. Our approach can be
easily deployed to traditional recurrent neural networks and fine-tuned
pre-trained transformers.

本文针对文本分类任务中的 OOD 检测问题，提出了基于证据不确定性的方法，该方法通过引入辅助的离群样本和伪样本来训练模型，并明确建模了类别概率的不确定性。实验证明，该方法能够轻松部署于传统 RNN 和 Fine-tuned 预训练 transformers，并在 OOD 检测上优于其他方法。