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...

Fuld beskrivelse

Bibliografiske detaljer
Main Authors:	La Malfa, E, Michelmore, R, Zbrzezny, AM, Paoletti, N, Kwiatkowska, M
Format:	Conference item
Sprog:	English
Udgivet:	International Joint Conferences on Artificial Intelligence 2021

Lignende værker

Statistical guarantees for the robustness of Bayesian neural networks
af: Cardelli, L, et al.
Udgivet: (2019)

Towards Faithful Model Explanation in NLP: A Survey
af: Qing Lyu, et al.
Udgivet: (2024-07-01)

Explanation-Based Human Debugging of NLP Models: A Survey
af: Piyawat Lertvittayakumjorn, et al.
Udgivet: (2021-01-01)

Robustness guarantees for deep neural networks on videos
af: Kwiatkowska, M, et al.
Udgivet: (2020)

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

The king is naked: On the notion of robustness for natural language processing
af: La Malfa, E, et al.
Udgivet: (2022)

Adversarial robustness guarantees for Gaussian processes
af: Patane, A, et al.
Udgivet: (2022)

Robustness guarantees for Bayesian inference with Gaussian processes
af: Cardelli, L, et al.
Udgivet: (2019)

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

Provable guarantees on the robustness of decision rules to causal interventions
af: Wang, B, et al.
Udgivet: (2021)

Probabilistic Guarantees in Robust Optimization
af: Bertsimas, Dimitris, et al.
Udgivet: (2022)

Adversarial robustness guarantees for classification with Gaussian Processes
af: Blaas, A, et al.
Udgivet: (2020)

Uncertainty quantification with statistical guarantees in end-to-end autonomous driving control
af: Michelmore, R, et al.
Udgivet: (2020)

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

Robustness guarantees for credal Bayesian networks via constraint relaxation over probabilistic circuits
af: Wijk, H, et al.
Udgivet: (2022)

Sample efficient model-free reinforcement learning from LTL specifications with optimality guarantees
af: Shao, D, et al.
Udgivet: (2023)

Global robustness evaluation of deep neural networks with provable guarantees for the Hamming distance
af: Ruan, W, et al.
Udgivet: (2019)

Efficient synthesis of robust models for stochastic systems
af: Calinescu, R, et al.
Udgivet: (2018)

On robustness for natural language processing
af: La Malfa, E
Udgivet: (2023)

Robust optimization for adversarial learning with finite sample complexity guarantees
af: Bertolace, A, et al.
Udgivet: (2024)

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

Robust Sampling-based Motion Planning with Asymptotic Optimality Guarantees
af: Karaman, Sertac, et al.
Udgivet: (2013)

Checking RTECTL properties of STSs via SMT-based Bounded Model Checking
af: Agnieszka Zbrzezny, et al.
Udgivet: (2015-12-01)

nlp /
af: Bavister, Steve, author 555926, et al.
Udgivet: (2004)

Bounded Model Checking for Metric Temporal Logic Properties of Timed Automata with Digital Clocks
af: Agnieszka M. Zbrzezny, et al.
Udgivet: (2022-12-01)

Assessing robustness of text classification through maximal safe radius computation
af: La Malfa, E, et al.
Udgivet: (2020)

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

Robust Variable Selection with Optimality Guarantees for High-Dimensional Logistic Regression
af: Luca Insolia, et al.
Udgivet: (2021-08-01)

Distributed robust Lasso-MPC based on Nash optimization for smart grid: Guaranteed robustness and stability
af: Hossein Ahmadian, et al.
Udgivet: (2024-11-01)

NLP City
af: Nguyen, Thanh P. Q.
Udgivet: (2024)

Essential NLP /
af: Bavister, Steve, author 555926, et al.
Udgivet: (2010)

SUCCESSFUL NLP /
af: Lazarus, Jeremy, author 651739
Udgivet: (2010)

Individual fairness guarantees for neural networks
af: Benussi, E, et al.
Udgivet: (2022)

RODES: A robust-design synthesis tool for probabilistic systems
af: Calinescu, R, et al.
Udgivet: (2017)

Robust pose estimation which guarantees positive depths
af: Chun Li, et al.
Udgivet: (2023-12-01)

Reduced-order neural network synthesis with robustness guarantees
af: Drummond, R, et al.
Udgivet: (2022)

The pipeline processing of NLP
af: Elov B. B., et al.
Udgivet: (2023-01-01)

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

Towards solving NLP tasks with optimal transport loss
af: Rishabh Bhardwaj, et al.
Udgivet: (2022-11-01)

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