Improving Generalizability in Implicitly Abusive Language Detection with Concept Activation Vectors.
Isar NejadgholiKathleen C. FraserSvetlana KiritchenkoPublished in: CoRR (2022)
Keyphrases
- false alarms
- detection rate
- natural language
- programming language
- detection algorithm
- object detection
- language processing
- detection method
- detection accuracy
- automatic detection
- feature vectors
- modeling language
- false positives
- language learning
- concept learning
- face detection
- information processing
- anomaly detection
- formal logic