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

EMNLP

Cite Paper Code

Authors

Dakuo Wang
Shiyu Chang
Ming Tan
Yang Yu
Haoyu Wang
Saloni Potdar
Mo Yu

Published on

11/07/2019

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 in machine learning applications we observe that training data is often insufficient. In this work, we propose an OOD-resistant Prototypical Network to tackle this zero-shot OOD detection and few-shot ID classification task. Evaluations 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.

Please cite our work using the BibTeX below.

@inproceedings{tan-etal-2019-domain,
    title = "Out-of-Domain Detection for Low-Resource Text Classification Tasks",
    author = "Tan, Ming  and
      Yu, Yang  and
      Wang, Haoyu  and
      Wang, Dakuo  and
      Potdar, Saloni  and
      Chang, Shiyu  and
      Yu, Mo",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/D19-1364",
    doi = "10.18653/v1/D19-1364",
    pages = "3566--3572",
}