Post-hoc Interpretability for Neural NLP: A Survey
ACM Computing Surveys · 31.08.2023 · 55 (8) · 1-42
DOI: 10.1145/3546577 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 23.12.2022. Verfasst von Andreas Madsen und 2 weiteren Autor:innen. Die Arbeit wurde bisher 176-mal zitiert (Crossref) und nennt 138 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Canada CIFAR AI Chairs program, NSERC Discovery.
Abstract (Originalsprache)
Neural networks for NLP are becoming increasingly complex and widespread, and there is a growing concern if these models are responsible to use. Explaining models helps to address the safety and ethical concerns and is essential for accountability. Interpretability serves to provide these explanations in terms that are understandable to humans. Additionally, post-hoc methods provide explanations after a model is learned and are generally model-agnostic. This survey provides a categorization of how recent post-hoc interpretability methods communicate explanations to humans, it discusses each method in-depth, and how they are validated, as the latter is often a common concern.
Förderung
- Canada CIFAR AI Chairs program
- NSERC Discovery
Zitieren
APA
Madsen, A., Reddy, S., & Chandar, S. (2023). Post-hoc Interpretability for Neural NLP: A Survey. ACM Computing Surveys, 55(8), 1-42. https://doi.org/10.1145/3546577
Vancouver
Madsen A, Reddy S, Chandar S. Post-hoc Interpretability for Neural NLP: A Survey. ACM Computing Surveys. 2023;55(8):1-42. doi:10.1145/3546577
BibTeX
@article{Madsen2023,
author = {Madsen, Andreas and Reddy, Siva and Chandar, Sarath},
title = {Post-hoc Interpretability for Neural NLP: A Survey},
journal = {ACM Computing Surveys},
year = {2023},
volume = {55},
number = {8},
pages = {1--42},
doi = {10.1145/3546577}
}
EUVIMED