COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks.
Fanny JourdanAgustin PicardThomas FelLaurent RisserJean-Michel LoubesNicholas AsherPublished in: CoRR (2023)
Keyphrases
- neural nets
- feed forward
- natural language processing
- back propagation
- backpropagation neural networks
- neural network
- learning tasks
- training data
- information extraction
- training examples
- counter propagation
- support vector
- data mining
- artificial neural networks
- question answering
- class labels
- classification algorithm
- data sets
- high dimensional
- sensitivity analysis
- natural language
- artificial intelligence
- learning algorithm
- tasks in natural language processing