Concept-Based Explanations to Test for False Causal Relationships Learned by Abusive Language Classifiers.
Isar NejadgholiSvetlana KiritchenkoKathleen C. FraserEsma BalkirPublished in: CoRR (2023)
Keyphrases
- causal relationships
- causal models
- causal discovery
- bayesian networks
- causal relations
- support vector
- causal structure
- structural descriptions
- decision trees
- training data
- causal effects
- natural language
- training set
- statistical tests
- influence diagrams
- structural model
- class labels
- feature set
- data mining
- conditional independence
- fuzzy cognitive maps
- data sets
- causal networks
- text categorization