Out-of-Domain Detection for Low-Resource Text Classification Tasks

2019/08/31 by Tan, Ming, Yu, Yang, Wang, Haoyu +4 · 1 citation
#Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.1909.05357

Abstract

Out-of-domain (OOD) detection for low-resource text classification is a realistic but understudied task. The goal is to detect the OOD cases with limited in-domain (ID) training data, since we observe that training data is often insufficient in machine learning applications. In this work, we propose an OOD-resistant Prototypical Network to tackle this zero-shot OOD detection and few-shot ID classification task. Evaluation on real-world datasets show that the proposed solution outperforms state-of-the-art methods in zero-shot OOD detection task, while maintaining a competitive performance on ID classification task.

Cited by

• IDALC: A Semi-Supervised Framework for Intent Detection and Active Learning based Correction

Related

• Towards Textual Out-of-Domain Detection without In-Domain Labels
• Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection
• Building One-class Detector for Anything: Open-vocabulary Zero-shot OOD Detection Using Text-image Models
• Unsupervised Out-of-Domain Detection via Pre-trained Transformers
• Harnessing Large Language and Vision-Language Models for Robust Out-of-Distribution Detection