Double Trouble: How to not Explain a Text Classifier’s Decisions Using Counterfactuals Synthesized by Masked Language Models?
647Knowledge Triples
| Source Entity | Relationship | Target Entity |
|---|---|---|
|
Маргинализация ввода
Method |
uses |
BERT
Method |
|
LIME
Method |
evaluatedBy |
Метрики ROAR
Metric |
|
LIME
Method |
improves |
BERT
Method |