In many real-world settings, machine learning models need to identify user inputs that are out-of-domain (OOD) so as to avoid performing wrong actions. This work focuses on a challenging case of OOD detection, where no labels for in-domain data are accessible (e.g., no intent labels for the intent classification task). To this end, we first evaluate different language model based approaches that predict likelihood for a sequence of tokens. Furthermore, we propose a novel representation learning based method by combining unsupervised clustering and contrastive learning so that better data representations for OOD detection can be learned. Through extensive experiments, we demonstrate that this method can significantly outperform likelihood-based methods and can be even competitive to the state-of-the-art supervised approaches with label information.

中文翻译：

---

实现没有域内标签的文本域外检测


在许多现实环境中，机器学习模型需要识别域外（OOD）的用户输入，以避免执行错误的操作。这项工作重点关注 OOD 检测的一个具有挑战性的案例，其中无法访问域内数据的标签（例如，没有意图分类任务的意图标签）。为此，我们首先评估基于不同语言模型的方法来预测标记序列的可能性。此外，我们提出了一种新的基于表示学习的方法，通过结合无监督聚类和对比学习，以便可以学习更好的 OOD 检测数据表示。通过大量的实验，我们证明该方法可以显着优于基于可能性的方法，甚至可以与最先进的带有标签信息的监督方法竞争。