Detecting out-of-domain (OOD) intents from user queries is essential for avoiding wrong operations in task-oriented dialogue systems. The key challenge is how to distinguish in-domain (IND) and OOD intents. Previous methods ignore the alignment between representation learning and scoring function, limiting the OOD detection performance. In this paper, we propose a unified neighborhood learning framework (UniNL) to detect OOD intents. Specifically, we design a K-nearest neighbor contrastive learning (KNCL) objective for representation learning and introduce a KNN-based scoring function for OOD detection. We aim to align representation learning with scoring function. Experiments and analysis on two benchmark datasets show the effectiveness of our method.
@article{arxiv.2210.10722,
title = {UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning},
author = {Yutao Mou and Pei Wang and Keqing He and Yanan Wu and Jingang Wang and Wei Wu and Weiran Xu},
journal= {arXiv preprint arXiv:2210.10722},
year = {2022}
}