On guaranteed optimal robust explanations for NLP models

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...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής
Κύριοι συγγραφείς:	La Malfa, E, Michelmore, R, Zbrzezny, AM, Paoletti, N, Kwiatkowska, M
Μορφή:	Conference item
Γλώσσα:	English
Έκδοση:	International Joint Conferences on Artificial Intelligence 2021

Παρόμοια τεκμήρια

Statistical guarantees for the robustness of Bayesian neural networks
ανά: Cardelli, L, κ.ά.
Έκδοση: (2019)

Towards Faithful Model Explanation in NLP: A Survey
ανά: Qing Lyu, κ.ά.
Έκδοση: (2024-07-01)

Explanation-Based Human Debugging of NLP Models: A Survey
ανά: Piyawat Lertvittayakumjorn, κ.ά.
Έκδοση: (2021-01-01)

Robustness guarantees for deep neural networks on videos
ανά: Kwiatkowska, M, κ.ά.
Έκδοση: (2020)

Safety and robustness for deep learning with provable guarantees (keynote)
ανά: Kwiatkowska, M
Έκδοση: (2019)

The king is naked: On the notion of robustness for natural language processing
ανά: La Malfa, E, κ.ά.
Έκδοση: (2022)

Adversarial robustness guarantees for Gaussian processes
ανά: Patane, A, κ.ά.
Έκδοση: (2022)

Robustness guarantees for Bayesian inference with Gaussian processes
ανά: Cardelli, L, κ.ά.
Έκδοση: (2019)

Safety and robustness for deep learning with provable guarantees (invited paper - keynote)
ανά: Kwiatkowska, M
Έκδοση: (2020)

Provable guarantees on the robustness of decision rules to causal interventions
ανά: Wang, B, κ.ά.
Έκδοση: (2021)

Probabilistic Guarantees in Robust Optimization
ανά: Bertsimas, Dimitris, κ.ά.
Έκδοση: (2022)

Adversarial robustness guarantees for classification with Gaussian Processes
ανά: Blaas, A, κ.ά.
Έκδοση: (2020)

Uncertainty quantification with statistical guarantees in end-to-end autonomous driving control
ανά: Michelmore, R, κ.ά.
Έκδοση: (2020)

Robustness guarantees for Bayesian neural networks (invited extended abstract of a keynote speaker)
ανά: Kwiatkowska, M
Έκδοση: (2022)

Robustness guarantees for credal Bayesian networks via constraint relaxation over probabilistic circuits
ανά: Wijk, H, κ.ά.
Έκδοση: (2022)

Sample efficient model-free reinforcement learning from LTL specifications with optimality guarantees
ανά: Shao, D, κ.ά.
Έκδοση: (2023)

Global robustness evaluation of deep neural networks with provable guarantees for the Hamming distance
ανά: Ruan, W, κ.ά.
Έκδοση: (2019)

Efficient synthesis of robust models for stochastic systems
ανά: Calinescu, R, κ.ά.
Έκδοση: (2018)

On robustness for natural language processing
ανά: La Malfa, E
Έκδοση: (2023)

Robust optimization for adversarial learning with finite sample complexity guarantees
ανά: Bertolace, A, κ.ά.
Έκδοση: (2024)

Guaranteed robustness properties of multivariable, nonlinear, stochastic optimal regulators
Έκδοση: (2003)

Robust Sampling-based Motion Planning with Asymptotic Optimality Guarantees
ανά: Karaman, Sertac, κ.ά.
Έκδοση: (2013)

Checking RTECTL properties of STSs via SMT-based Bounded Model Checking
ανά: Agnieszka Zbrzezny, κ.ά.
Έκδοση: (2015-12-01)

nlp /
ανά: Bavister, Steve, author 555926, κ.ά.
Έκδοση: (2004)

Bounded Model Checking for Metric Temporal Logic Properties of Timed Automata with Digital Clocks
ανά: Agnieszka M. Zbrzezny, κ.ά.
Έκδοση: (2022-12-01)

Assessing robustness of text classification through maximal safe radius computation
ανά: La Malfa, E, κ.ά.
Έκδοση: (2020)

Safety verification for deep neural networks with provable guarantees
ανά: Kwiatkowska, M
Έκδοση: (2019)

Robust Variable Selection with Optimality Guarantees for High-Dimensional Logistic Regression
ανά: Luca Insolia, κ.ά.
Έκδοση: (2021-08-01)

Distributed robust Lasso-MPC based on Nash optimization for smart grid: Guaranteed robustness and stability
ανά: Hossein Ahmadian, κ.ά.
Έκδοση: (2024-11-01)

NLP City
ανά: Nguyen, Thanh P. Q.
Έκδοση: (2024)

Essential NLP /
ανά: Bavister, Steve, author 555926, κ.ά.
Έκδοση: (2010)

SUCCESSFUL NLP /
ανά: Lazarus, Jeremy, author 651739
Έκδοση: (2010)

Individual fairness guarantees for neural networks
ανά: Benussi, E, κ.ά.
Έκδοση: (2022)

RODES: A robust-design synthesis tool for probabilistic systems
ανά: Calinescu, R, κ.ά.
Έκδοση: (2017)

Robust pose estimation which guarantees positive depths
ανά: Chun Li, κ.ά.
Έκδοση: (2023-12-01)

Reduced-order neural network synthesis with robustness guarantees
ανά: Drummond, R, κ.ά.
Έκδοση: (2022)

The pipeline processing of NLP
ανά: Elov B. B., κ.ά.
Έκδοση: (2023-01-01)

Dimensions of Explanatory Value in NLP Models
ανά: Kees van Deemter
Έκδοση: (2023-12-01)

Towards solving NLP tasks with optimal transport loss
ανά: Rishabh Bhardwaj, κ.ά.
Έκδοση: (2022-11-01)

Robustness evaluation of deep neural networks with provable guarantees
ανά: Wu, M
Έκδοση: (2020)