UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning
This addresses the challenge of distinguishing in-domain and out-of-domain intents to avoid wrong operations in dialogue systems, representing an incremental improvement over previous methods.
The paper tackled the problem of detecting out-of-domain intents in task-oriented dialogue systems by proposing UniNL, a unified neighborhood learning framework that aligns representation learning with scoring function, resulting in improved OOD detection performance as shown on two benchmark datasets.
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.