Login / Signup
Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?
Peter Hase
Shiyue Zhang
Harry Xie
Mohit Bansal
Published in:
EMNLP (Findings) (2020)
Keyphrases
</>
natural language
prior knowledge
probabilistic model
information extraction
data mining
artificial intelligence
natural language processing
question answering
experimental data
statistical models
computational models
language processing
physical systems