Contextualizing Hate Speech Classifiers with Post-hoc Explanation.
Brendan KennedyXisen JinAida Mostafazadeh DavaniMorteza DehghaniXiang RenPublished in: ACL (2020)
Keyphrases
- post hoc
- speech recognition
- lexical features
- training data
- linear classifiers
- supervised classification
- decision trees
- training samples
- data sets
- causal reasoning
- classifier combination
- speech signal
- machine learning algorithms
- training examples
- recognition engine
- classification method
- classification rate
- training set
- support vector
- classification systems
- explanation based learning
- decision boundary
- feature selection
- multiple classifiers
- classification decisions
- speech synthesis
- ensemble learning
- svm classifier
- naive bayes
- learning algorithm