Skip to main navigation Skip to search Skip to main content

Open-Set Semi-Supervised Text Classification with Latent Outlier Softening

  • Beihang University
  • University of Ottawa

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Semi-supervised text classification (STC) has been extensively researched and reduces human annotation. However, existing research assuming that unlabeled data only contains in-distribution texts is unrealistic. This paper extends STC to a more practical Open-set Semi-supervised Text Classification (OSTC) setting, which assumes that the unlabeled data contains out-of-distribution (OOD) texts. The main challenge in OSTC is the false positive inference problem caused by inadvertently including OOD texts during training. To address the problem, we first develop baseline models using outlier detectors for hard OOD-data filtering in a pipeline procedure. Furthermore, we propose a Latent Outlier Softening (LOS) framework that integrates semi-supervised training and outlier detection within probabilistic latent variable modeling. LOS softens the OOD impacts by the Expectation-Maximization (EM) algorithm and weighted entropy maximization. Experiments on 3 created datasets show that LOS significantly outperforms baselines.

Original languageEnglish
Title of host publicationKDD 2023 - Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
PublisherAssociation for Computing Machinery
Pages226-236
Number of pages11
ISBN (Electronic)9798400701030
DOIs
StatePublished - 4 Aug 2023
Event29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023 - Long Beach, United States
Duration: 6 Aug 202310 Aug 2023

Publication series

NameProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
ISSN (Print)2154-817X

Conference

Conference29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023
Country/TerritoryUnited States
CityLong Beach
Period6/08/2310/08/23

Keywords

  • latent variable
  • semi-supervised learning
  • text classification

Fingerprint

Dive into the research topics of 'Open-Set Semi-Supervised Text Classification with Latent Outlier Softening'. Together they form a unique fingerprint.

Cite this