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: CoRR (2021)
Keyphrases
- language model
- text classifiers
- text classification
- language modeling
- text categorization
- document retrieval
- n gram
- probabilistic model
- document classification
- information retrieval
- naive bayes
- retrieval model
- text data
- query expansion
- test collection
- translation model
- smoothing methods
- pattern recognition
- structured data
- naive bayes classifier
- learning algorithm
- machine learning