基于协方差校正马氏距离的小样本域外意图检测
Few-Shot Out of Domain Intent Detection with Covariance Corrected Mahalanobis Distance
浏览论文内容
中文总结 AI 辅助
本文针对现有马氏距离法在小样本域外意图检测中性能不及基线的问题，分析原因并提出协方差校正马氏距离法，以提升小样本场景下的域外意图检测性能。
中文摘要 AI 辅助
聊天机器人、语音助手等对话智能体经过训练以理解并响应用户意图，当遇到训练未覆盖的意图的话语时，需将其分类为“未知”或“域外（OOD）”意图，此即域外意图检测问题。Podolskiy等人（2021）表明马氏距离可有效识别域外意图，性能优于其他方法，但该方法在实用的小样本场景中未优于基线。本文分析其低性能原因，提出协方差校正马氏距离用于检测域外意图。
英文摘要
Conversational agents like chatbots and voice assistants are trained to understand and respond to user intents. On encountering an utterance with an intent different from the ones they have been trained on, these agents are expected to classify the intent as `unknown' or `out of domain'. This problem is known as out of domain (OOD) intent detection. Podolskiy et al. (2021), showed that Mahalanobis distance can be used effectively for identifying OOD intents, outperforming competing approaches. However, their method fails to outperform the baselines in the practically important few-shot setting. In this paper we analyze the reason for low performance and propose a covariance corrected Mahalanobis distance for detecting out-of-domain intents.
发表机构
- Amazon（亚马逊）
机构由 AI 辅助整理，请以论文原文为准。
