Out-of-Domain (OOD) intent detection is important for practical dialog systems. To alleviate the issue of lacking OOD training samples, some works propose synthesizing pseudo OOD samples and directly assigning one-hot OOD labels to these pseudo samples. However, these one-hot labels introduce noises to the training process because some hard pseudo OOD samples may coincide with In-Domain (IND) intents. In this paper, we propose an adaptive soft pseudo labeling (ASoul) method that can estimate soft labels for pseudo OOD samples when training OOD detectors. Semantic connections between pseudo OOD samples and IND intents are captured using an embedding graph. A co-training framework is further introduced to produce resulting soft labels following the smoothness assumption, i.e., close samples are likely to have similar labels. Extensive experiments on three benchmark datasets show that ASoul consistently improves the OOD detection performance and outperforms various competitive baselines.

翻译：为了减轻缺乏OOD培训样品的问题,有些工作提议将伪OOD样品合成为合成OOD样品,并直接为这些假样品分配一热OOD标签,然而,这些单热标签给培训过程带来噪音,因为一些硬伪OOD样品可能与在Domain(IND)的意图相吻合。在本文件中,我们建议采用适应性软假标签(Aoul)方法,在培训OOD探测器时,可以估计假OOOD样品的软标签。使用嵌入图采集伪OOOD样品与IND意图之间的语义联系。进一步引入了共同培训框架,以便在平稳假设后产生产生的软标签,即近距离样品可能具有类似的标签。关于三个基准数据集的广泛实验表明,Asoul不断改进OOD探测性,超越各种竞争性基线。