Conference item
On guaranteed optimal robust explanations for NLP models
- Abstract:
-
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 user-defined cost function, such as the length of explanation, and robustness, in that they ensure prediction invariance for any bounded perturbation in the embedding space of the left-out words. We...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Authors
Funding
Bibliographic Details
- Publisher:
- International Joint Conferences on Artificial Intelligence Publisher's website
- Host title:
- Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
- Pages:
- 2658-2665
- Publication date:
- 2021-08-11
- Acceptance date:
- 2021-04-29
- Event title:
- 30th International Joint Conference on Artificial Intelligence (IJCAI-21)
- Event location:
- Montreal, Canada (virtual)
- Event website:
- https://ijcai-21.org/
- Event start date:
- 2021-08-21
- Event end date:
- 2021-08-26
- DOI:
- EISBN:
- 9780999241196
Item Description
- Language:
- English
- Keywords:
- Pubs id:
-
1176094
- Local pid:
- pubs:1176094
- Deposit date:
- 2021-05-12
Terms of use
- Copyright holder:
- International Joint Conferences on Artificial Intelligence
- Copyright date:
- 2021
- Rights statement:
- Copyright © 2021 International Joint Conferences on Artificial Intelligence. All rights reserved.
- Notes:
- This paper was presented at the 30th International Joint Conference on Artificial Intelligence (IJCAI-21), 21-26 August 2021, Montreal, Canada (virtual).
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record