Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discovery
This addresses the challenge of developing new skills in dialogue systems, though it appears incremental as it builds on prior contrastive learning approaches.
The paper tackles the problem of discovering out-of-domain intents in task-oriented dialogue systems by proposing a unified K-nearest neighbor contrastive learning framework, achieving substantial improvements over state-of-the-art methods on three benchmark datasets.
Discovering out-of-domain (OOD) intent is important for developing new skills in task-oriented dialogue systems. The key challenges lie in how to transfer prior in-domain (IND) knowledge to OOD clustering, as well as jointly learn OOD representations and cluster assignments. Previous methods suffer from in-domain overfitting problem, and there is a natural gap between representation learning and clustering objectives. In this paper, we propose a unified K-nearest neighbor contrastive learning framework to discover OOD intents. Specifically, for IND pre-training stage, we propose a KCL objective to learn inter-class discriminative features, while maintaining intra-class diversity, which alleviates the in-domain overfitting problem. For OOD clustering stage, we propose a KCC method to form compact clusters by mining true hard negative samples, which bridges the gap between clustering and representation learning. Extensive experiments on three benchmark datasets show that our method achieves substantial improvements over the state-of-the-art methods.