Unknown intent detection aims to identify the out-of-distribution (OOD) utterance whose intent has never appeared in the training set. In this paper, we propose using energy scores for this task as the energy score is theoretically aligned with the density of the input and can be derived from any classifier. However, high-quality OOD utterances are required during the training stage in order to shape the energy gap between OOD and in-distribution (IND), and these utterances are difficult to collect in practice. To tackle this problem, we propose a data manipulation framework to Generate high-quality OOD utterances with importance weighTs (GOT). Experimental results show that the energy-based detector fine-tuned by GOT can achieve state-of-the-art results on two benchmark datasets.

翻译：未知意图探测旨在确定培训中从未出现过其意图的分发(OOOD)外语。本文建议,在这项工作中使用能源分数,因为能源分数理论上与输入密度一致,可以从任何分类中得出。然而,在培训阶段需要高质量的OOOD出量,以便形成OOD和在分发(IND)之间的能源差距,而这些分数在实践中难以收集。为了解决这一问题,我们提议了一个数据操纵框架,用于生成具有重要性的高质量OOOOD出量(重力称Ts ) 。实验结果显示,由TORT微调的基于能源的探测器可以在两个基准数据集上取得最先进的结果。