Double Trouble: How to not Explain a Text Classifier's Decisions Using Counterfactuals Synthesized by Masked Language Models?
Thang M. PhamTrung BuiLong MaiAnh NguyenPublished in: AACL/IJCNLP (1) (2022)
Keyphrases
- language model
- text classifiers
- text classification
- language modeling
- text categorization
- probabilistic model
- n gram
- naive bayes
- document retrieval
- information retrieval
- retrieval model
- query expansion
- document classification
- test collection
- text data
- smoothing methods
- vector space model
- feature selection
- classification accuracy
- support vector
- svm classifier
- natural language processing
- active learning
- naive bayes classification
- language models for information retrieval