English

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

Computation and Language 2019-09-13 v1 Machine Learning Machine Learning

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.

Keywords

Cite

@article{arxiv.1909.05357,
  title  = {Out-of-Domain Detection for Low-Resource Text Classification Tasks},
  author = {Ming Tan and Yang Yu and Haoyu Wang and Dakuo Wang and Saloni Potdar and Shiyu Chang and Mo Yu},
  journal= {arXiv preprint arXiv:1909.05357},
  year   = {2019}
}

Comments

EMNLP 2019

R2 v1 2026-06-23T11:12:52.486Z