Contextualizing Hate Speech Classifiers with Post-hoc Explanation
Hate speech classifiers trained on imbalanced datasets struggle to determine if group identifiers like "gay" or "black" are used in offensive or prejudiced ways. Such biases manifest in false positives when these identifiers are present, due to models' inability to learn the contexts which constitute a hateful usage of identifiers. We extract SOC post-hoc explanations from fine-tuned BERT classifiers to efficiently detect bias towards identity terms. Then, we propose a novel regularization technique based on these explanations that encourages models to learn from the context of group identifiers in addition to the identifiers themselves. Our approach improved over baselines in limiting false positives on out-of-domain data while maintaining or improving in-domain performance. Project page: https://inklab.usc.edu/contextualize-hate-speech/.
Code (3)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Reproducibility Report: Contextualizing Hate Speech Classifiers with Post-hoc Explanation
The presented report evaluates Contextualizing Hate Speech Classifiers with Post-hoc Explanation paper within the scope of ML Reproducibility Challenge 2020. Our work focuses on both aspects constituting the paper: the m…
Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection
Transformer-based Natural Language Processing models have become the standard for hate speech detection. However, the unconscious use of these techniques for such a critical task comes with negative consequences. Various…
BenchmarkingHate Speech DetectionExplain the Flag: Contextualizing Hate Speech Beyond Censorship
Hate, derogatory, and offensive speech remains a persistent challenge in online platforms and public discourse. While automated detection systems are widely used, most focus on censorship or removal, raising concerns for…
Hate Speech DetectionAligning Attention with Human Rationales for Self-Explaining Hate Speech Detection
The opaque nature of deep learning models presents significant challenges for the ethical deployment of hate speech detection systems. To address this limitation, we introduce Supervised Rational Attention (SRA), a frame…
Hate Speech DetectionContextualizing Internet Memes Across Social Media Platforms
Internet memes have emerged as a novel format for communication and expressing ideas on the web. Their fluidity and creative nature are reflected in their widespread use, often across platforms and occasionally for uneth…
Hate Speech Detection