Out-of-Domain (OOD) detection is a key component in a task-oriented dialog
system, which aims to identify whether a query falls outside the predefined
supported intent set. Previous softmax-based detection algorithms are proved to
be overconfident for OOD samples. In this paper, we analyze overconfident OOD
comes from distribution uncertainty due to the mismatch between the training
and test distributions, which makes the model can't confidently make
predictions thus probably causing abnormal softmax scores. We propose a
Bayesian OOD detection framework to calibrate distribution uncertainty using
Monte-Carlo Dropout. Our method is flexible and easily pluggable into existing
softmax-based baselines and gains 33.33\% OOD F1 improvements with increasing
only 0.41\% inference time compared to MSP. Further analyses show the
effectiveness of Bayesian learning for OOD detection.

本文提出了一种基于贝叶斯模型和 Monte-Carlo Dropout 技术的 OOD 检测框架，能够有效减少训练集和测试集分布的不匹配所导致的不确定性，从而提高 OOD 的 F1 得分。