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.

本文提出了一种 K 最近邻对比学习框架，用于在任务导向式对话系统中发现 OOI，它具有两个阶段：IND 预训练和 OOD 聚类。实验结果表明，该方法在三个基准数据集上取得了超越现有技术的显着改进。