Papers › Self-Attentive, Multi-Context One-Class Classification for Unsupervised Anomaly...

Self-Attentive, Multi-Context One-Class Classification for Unsupervised Anomaly Detection on Text

1 Jul 2019ACL 2019 7archive 2025-07-28

Lukas Ruff, Yury Zemlyanskiy, V, Robert ermeulen, Thomas Schnake, Marius Kloft

There exist few text-specific methods for unsupervised anomaly detection, and for those that do exist, none utilize pre-trained models for distributed vector representations of words. In this paper we introduce a new anomaly detection method{---}Context Vector Data Description (CVDD){---}which builds upon word embedding models to learn multiple sentence representations that capture multiple semantic contexts via the self-attention mechanism. Modeling multiple contexts enables us to perform contextual anomaly detection of sentences and phrases with respect to the multiple themes and concepts present in an unlabeled text corpus. These contexts in combination with the self-attention weights make our method highly interpretable. We demonstrate the effectiveness of CVDD quantitatively as well as qualitatively on the well-known Reuters, 20 Newsgroups, and IMDB Movie Reviews datasets.

PaperPDFCode

Code

lukasruff/CVDD-PyTorch officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Anomaly DetectionContextual Anomaly DetectionGeneral ClassificationOne-Class ClassificationSentenceUnsupervised Anomaly Detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections