APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Pei, He, Keqing, Mou, Yutao, Song, Xiaoshuai, Wu, Yanan, Wang, Jingang, Xian, Yunsen, Cai, Xunliang, Xu, Weiran
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929252213981184
author Wang, Pei
He, Keqing
Mou, Yutao
Song, Xiaoshuai
Wu, Yanan
Wang, Jingang
Xian, Yunsen
Cai, Xunliang
Xu, Weiran
author_facet Wang, Pei
He, Keqing
Mou, Yutao
Song, Xiaoshuai
Wu, Yanan
Wang, Jingang
Xian, Yunsen
Cai, Xunliang
Xu, Weiran
contents Detecting out-of-domain (OOD) intents from user queries is essential for a task-oriented dialogue system. Previous OOD detection studies generally work on the assumption that plenty of labeled IND intents exist. In this paper, we focus on a more practical few-shot OOD setting where there are only a few labeled IND data and massive unlabeled mixed data that may belong to IND or OOD. The new scenario carries two key challenges: learning discriminative representations using limited IND data and leveraging unlabeled mixed data. Therefore, we propose an adaptive prototypical pseudo-labeling (APP) method for few-shot OOD detection, including a prototypical OOD detection framework (ProtoOOD) to facilitate low-resource OOD detection using limited IND data, and an adaptive pseudo-labeling method to produce high-quality pseudo OOD\&IND labels. Extensive experiments and analysis demonstrate the effectiveness of our method for few-shot OOD detection.
format Preprint
id arxiv_https___arxiv_org_abs_2310_13380
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection
Wang, Pei
He, Keqing
Mou, Yutao
Song, Xiaoshuai
Wu, Yanan
Wang, Jingang
Xian, Yunsen
Cai, Xunliang
Xu, Weiran
Computation and Language
Detecting out-of-domain (OOD) intents from user queries is essential for a task-oriented dialogue system. Previous OOD detection studies generally work on the assumption that plenty of labeled IND intents exist. In this paper, we focus on a more practical few-shot OOD setting where there are only a few labeled IND data and massive unlabeled mixed data that may belong to IND or OOD. The new scenario carries two key challenges: learning discriminative representations using limited IND data and leveraging unlabeled mixed data. Therefore, we propose an adaptive prototypical pseudo-labeling (APP) method for few-shot OOD detection, including a prototypical OOD detection framework (ProtoOOD) to facilitate low-resource OOD detection using limited IND data, and an adaptive pseudo-labeling method to produce high-quality pseudo OOD\&IND labels. Extensive experiments and analysis demonstrate the effectiveness of our method for few-shot OOD detection.
title APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection
topic Computation and Language
url https://arxiv.org/abs/2310.13380