Back to Search
Start Over
Contextualizing Hate Speech Classifiers with Post-hoc Explanation
- Source :
- ACL
- Publication Year :
- 2020
- Publisher :
- Association for Computational Linguistics, 2020.
-
Abstract
- 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/.<br />Comment: To appear in Proceedings of the 2020 Annual Conference of the Association for Computational Linguistics; Updated references and discussions
- Subjects :
- FOS: Computer and information sciences
Computer Science - Machine Learning
Post hoc
Computer science
Identity (social science)
Context (language use)
02 engineering and technology
010501 environmental sciences
computer.software_genre
01 natural sciences
Computer Science - Information Retrieval
Machine Learning (cs.LG)
020204 information systems
0202 electrical engineering, electronic engineering, information engineering
False positive paradox
Regularization (linguistics)
0105 earth and related environmental sciences
Computer Science - Computation and Language
business.industry
Offensive
Identifier
Artificial intelligence
business
Computation and Language (cs.CL)
computer
Information Retrieval (cs.IR)
Natural language processing
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Accession number :
- edsair.doi.dedup.....44077cf85924b981706eb65c651c70e7