论文标题
公制学习和自适应边界用于域外检测
Metric Learning and Adaptive Boundary for Out-of-Domain Detection
论文作者
论文摘要
对话代理通常是为封闭世界环境设计的。不幸的是，用户可能会出乎意料的行为。基于开放世界的环境，我们经常遇到培训和测试数据是从不同分布中采样的情况。然后，来自不同分布的数据被称为室外（OOD）。强大的对话剂需要对这些OOD话语做出充分的反应。因此，强调了强大的OOD检测的重要性。不幸的是，收集OOD数据是一项具有挑战性的任务。我们设计了一种独立于OOD数据的OOD检测算法，该算法的表现优于公开可用数据集上的各种当前最新算法。我们的算法基于一种简单但有效的方法，即将度量学习与自适应决策边界相结合。此外，与其他算法相比，我们发现我们提出的算法在较低的类别的情况下显着改善了OOD的性能，同时保留了内域（IND）类的准确性。
Conversational agents are usually designed for closed-world environments. Unfortunately, users can behave unexpectedly. Based on the open-world environment, we often encounter the situation that the training and test data are sampled from different distributions. Then, data from different distributions are called out-of-domain (OOD). A robust conversational agent needs to react to these OOD utterances adequately. Thus, the importance of robust OOD detection is emphasized. Unfortunately, collecting OOD data is a challenging task. We have designed an OOD detection algorithm independent of OOD data that outperforms a wide range of current state-of-the-art algorithms on publicly available datasets. Our algorithm is based on a simple but efficient approach of combining metric learning with adaptive decision boundary. Furthermore, compared to other algorithms, we have found that our proposed algorithm has significantly improved OOD performance in a scenario with a lower number of classes while preserving the accuracy for in-domain (IND) classes.
