English

Deep Anomaly Detection in Text

Computation and Language 2024-01-09 v1 Artificial Intelligence

Abstract

Deep anomaly detection methods have become increasingly popular in recent years, with methods like Stacked Autoencoders, Variational Autoencoders, and Generative Adversarial Networks greatly improving the state-of-the-art. Other methods rely on augmenting classical models (such as the One-Class Support Vector Machine), by learning an appropriate kernel function using Neural Networks. Recent developments in representation learning by self-supervision are proving to be very beneficial in the context of anomaly detection. Inspired by the advancements in anomaly detection using self-supervised learning in the field of computer vision, this thesis aims to develop a method for detecting anomalies by exploiting pretext tasks tailored for text corpora. This approach greatly improves the state-of-the-art on two datasets, 20Newsgroups, and AG News, for both semi-supervised and unsupervised anomaly detection, thus proving the potential for self-supervised anomaly detectors in the field of natural language processing.

Keywords

Cite

@article{arxiv.2401.02971,
  title  = {Deep Anomaly Detection in Text},
  author = {Andrei Manolache},
  journal= {arXiv preprint arXiv:2401.02971},
  year   = {2024}
}

Comments

M.Sc. thesis, University of Bucharest, Faculty of Mathematics and Computer Sciences, 2021

R2 v1 2026-06-28T14:09:46.182Z