Estimating Soft Labels for Out-of-Domain Intent Detection. (arXiv:2211.05561v1 [cs.CL])

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 …

arxiv detection intent detection labels