Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning
This addresses a key challenge in task-oriented dialog systems for better handling unknown user queries, though it appears incremental as it builds on existing contrastive learning methods.
The paper tackles the problem of detecting out-of-domain intents in dialog systems by learning discriminative semantic features, achieving improved performance through supervised contrastive learning and adversarial augmentation as validated on two public datasets.
Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-oriented dialog system. A key challenge of OOD detection is to learn discriminative semantic features. Traditional cross-entropy loss only focuses on whether a sample is correctly classified, and does not explicitly distinguish the margins between categories. In this paper, we propose a supervised contrastive learning objective to minimize intra-class variance by pulling together in-domain intents belonging to the same class and maximize inter-class variance by pushing apart samples from different classes. Besides, we employ an adversarial augmentation mechanism to obtain pseudo diverse views of a sample in the latent space. Experiments on two public datasets prove the effectiveness of our method capturing discriminative representations for OOD detection.