Adversarial Training for Satire Detection: Controlling for Confounding Variables
This work addresses the issue of poor generalization in satire detection for applications like knowledge base population, though it is incremental in improving model robustness.
The paper tackled the problem of satire detection by addressing confounding variables like publication source, proposing an adversarial training model that achieved comparable classification performance while reducing source bias on a new German news dataset.
The automatic detection of satire vs. regular news is relevant for downstream applications (for instance, knowledge base population) and to improve the understanding of linguistic characteristics of satire. Recent approaches build upon corpora which have been labeled automatically based on article sources. We hypothesize that this encourages the models to learn characteristics for different publication sources (e.g., "The Onion" vs. "The Guardian") rather than characteristics of satire, leading to poor generalization performance to unseen publication sources. We therefore propose a novel model for satire detection with an adversarial component to control for the confounding variable of publication source. On a large novel data set collected from German news (which we make available to the research community), we observe comparable satire classification performance and, as desired, a considerable drop in publication classification performance with adversarial training. Our analysis shows that the adversarial component is crucial for the model to learn to pay attention to linguistic properties of satire.