Camouflaged Chinese Spam Content Detection with Semi-supervised Generative Active Learning
ACL, pp. 3080-3085, 2020.
We propose a supervIsed GeNerative Active Learning model for Chinese text spam detection
We propose a Semi-supervIsed GeNerative Active Learning (SIGNAL) model to address the imbalance, efficiency, and text camouflage problems of Chinese text spam detection task. A “self-diversity” criterion is proposed for measuring the “worthiness” of a candidate for annotation. A semi-supervised variational autoencoder with masked attentio...More
PPT (Upload PPT)