Uninformative Input Features and Counterfactual Invariance: Two Perspectives on Spurious Correlations in Natural Language.
Jacob EisensteinPublished in: CoRR (2022)
Keyphrases
- input features
- natural language
- machine learning algorithms
- feature selection
- feature values
- classification algorithm
- machine learning
- activation function
- class labels
- selected features
- support vector machine
- feature subset
- k nearest neighbor
- natural language processing
- information extraction
- data mining
- neural nets
- supervised learning
- labeled examples
- knn