no code implementations • 11 Jan 2023 • Atticus Geiger, Chris Potts, Thomas Icard
A faithful and interpretable explanation of an AI model's behavior and internal structure is a high-level explanation that is human-intelligible but also consistent with the known, but often opaque low-level causal details of the model.
no code implementations • IJCNLP 2019 • Atticus Geiger, Ignacio Cases, Lauri Karttunen, Chris Potts
Deep learning models for semantics are generally evaluated using naturalistic corpora.