论文标题
通过基于能量的学习来删除置域意图检测的置信度得分分布
Disentangling Confidence Score Distribution for Out-of-Domain Intent Detection with Energy-Based Learning
论文作者
论文摘要
在以任务为导向的对话框系统中，检测到室外（OOD）或用户查询的未知意图是必不可少的。传统的基于软马克斯的置信分数容易受到过度自信的问题。在本文中，我们提出了一个简单但强大的基于能量的得分函数，以检测OOD样品的能量得分高于IND样品的OOD。此外，考虑到一小部分标记的OOD样品，我们引入了一个基于能量的边缘目标，以进行监督的OOD检测，以明确将OOD样品与IND区分开。全面的实验和分析证明我们的方法有助于解开IND和OOD数据的置信度得分分布。\ footNote {我们的代码可在\ url {https://github.com/pris-nlp/emnlp/emnlp/emnlp2022-energy_orgy_ood/}。}。
Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-oriented dialog system. Traditional softmax-based confidence scores are susceptible to the overconfidence issue. In this paper, we propose a simple but strong energy-based score function to detect OOD where the energy scores of OOD samples are higher than IND samples. Further, given a small set of labeled OOD samples, we introduce an energy-based margin objective for supervised OOD detection to explicitly distinguish OOD samples from INDs. Comprehensive experiments and analysis prove our method helps disentangle confidence score distributions of IND and OOD data.\footnote{Our code is available at \url{https://github.com/pris-nlp/EMNLP2022-energy_for_OOD/}.}
