COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP.
Fanny JourdanAgustin PicardThomas FelLaurent RisserJean-Michel LoubesNicholas AsherPublished in: ACL (Findings) (2023)
Keyphrases
- neural nets
- feed forward
- natural language processing
- back propagation
- backpropagation neural networks
- training data
- decision trees
- artificial neural networks
- counter propagation
- neural network
- information extraction
- feature selection
- question answering
- machine learning
- real time
- learning tasks
- information retrieval
- single layer