Post-hoc Interpretability for Neural NLP: A Survey.
Andreas MadsenSiva ReddySarath ChandarPublished in: CoRR (2021)
Keyphrases
- post hoc
- natural language processing
- network architecture
- neural network
- bio inspired
- prediction accuracy
- free text
- information extraction
- natural language
- neural architecture
- neural model
- field of natural language processing
- machine translation
- question answering
- artificial neural
- text mining
- nonlinear predictive control
- computational neuroscience
- text analysis
- associative memory
- rule base
- expert systems
- wordnet
- computational intelligence
- decision trees
- language processing
- computational linguistics
- data sets
- linguistic analysis
- recurrent networks
- natural language learning
- information retrieval
- neural computation