2022/10/13 by Yunhua Zhou, Zhou, Yunhua, Wang, Pengyu +6
Computer Science · #Adversarial Robustness in Machine Learning #Computation and Language (cs.CL) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2210.07071
openalex publication_date 2022/10/13 · openalex created_date 2022/10/15 · openalex updated_date 2026/07/28
Most existing methods of Out-of-Domain (OOD) intent classification rely on extensive auxiliary OOD corpora or specific training paradigms. However, they are underdeveloped in the underlying principle that the models should have differentiated confidence in In- and Out-of-domain intent. In this work, we shed light on the fundamental cause of model overconfidence on OOD and demonstrate that calibrated subnetworks can be uncovered by pruning the overparameterized model. Calibrated confidence provided by the subnetwork can better distinguish In- and Out-of-domain, which can be a benefit for almost all post hoc methods. In addition to bringing fundamental insights, we also extend the Lottery Ticket Hypothesis to open-world scenarios. We conduct extensive experiments on four real-world datasets to demonstrate our approach can establish consistent improvements compared with a suite of competitive baselines.