On guaranteed optimal robust explanations for NLP models
We build on abduction-based explanations for machine learning and develop a method for computing local explanations for neural network models in natural language processing (NLP). Our explanations comprise a subset of the words of the input text that satisfies two key features: optimality w.r.t. a u...
Hauptverfasser: | La Malfa, E, Michelmore, R, Zbrzezny, AM, Paoletti, N, Kwiatkowska, M |
---|---|
Format: | Conference item |
Sprache: | English |
Veröffentlicht: |
International Joint Conferences on Artificial Intelligence
2021
|
Ähnliche Einträge
Ähnliche Einträge
-
Statistical guarantees for the robustness of Bayesian neural networks
von: Cardelli, L, et al.
Veröffentlicht: (2019) -
Towards Faithful Model Explanation in NLP: A Survey
von: Qing Lyu, et al.
Veröffentlicht: (2024-07-01) -
Explanation-Based Human Debugging of NLP Models: A Survey
von: Piyawat Lertvittayakumjorn, et al.
Veröffentlicht: (2021-01-01) -
Robustness guarantees for deep neural networks on videos
von: Kwiatkowska, M, et al.
Veröffentlicht: (2020) -
Safety and robustness for deep learning with provable guarantees (keynote)
von: Kwiatkowska, M
Veröffentlicht: (2019)