论文标题
UNINL：通过统一的邻里学习对准表示学习与OOD检测的评分函数
UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning
论文作者
论文摘要
从用户查询中检测室外（OOD）意图对于避免在以任务为导向的对话系统中进行错误操作至关重要。关键挑战是如何区分内域（IND）和OOD意图。先前的方法忽略表示学习和评分函数之间的对齐，从而限制了OOD检测性能。在本文中，我们提出了一个统一的邻里学习框架（UNINL）来检测OOD意图。具体而言，我们设计了一个最近的邻居对比学习（KNCL）目标，以实现表示学习，并引入基于KNN的评分功能以进行OOD检测。我们的目标是使表示能力与评分功能保持一致。两个基准数据集的实验和分析显示了我们方法的有效性。
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.
