Conference item icon

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


Access Document


Files:
Publisher copy:
10.24963/ijcai.2021/366

Authors


More by this author
Institution:
University of Oxford
Oxford college:
Trinity College
Role:
Author
More by this author
Institution:
University of Oxford
Oxford college:
Balliol College
Role:
Author
ORCID:
0000-0003-0906-1291
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author
ORCID:
0000-0001-9022-7599
Publisher:
International Joint Conferences on Artificial Intelligence Publisher's website
Pages:
2658-2665
Host title:
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
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:
2021-08-21T00:00:00Z
Event end date:
2021-08-26T00:00:00Z
DOI:
EISBN:
9780999241196
Language:
English
Keywords:
Pubs id:
1176094
Local pid:
pubs:1176094
Deposit date:
2021-05-12

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP