@inproceedings{Dejl:2021,
author = {Dejl, A and He, P and Mangal, P and Mohsin, H and Surdu, B and Voinea, E and Albini, E and Lertvittayakumjorn, P and Rago, A and Toni, F},
pages = {1761--1763},
publisher = {ACM},
title = {Argflow: a toolkit for deep argumentative explanations for neural networks.},
url = {https://dl.acm.org/doi/proceedings/10.5555/3463952?tocHeading=heading1},
year = {2021}
}

Download

TY  - CPAPER
AB  - In recent years, machine learning (ML) models have been successfully applied in a variety of real-world applications. However, theyare often complex and incomprehensible to human users. This candecrease trust in their outputs and render their usage in criticalsettings ethically problematic. As a result, several methods for explaining such ML models have been proposed recently, in particularfor black-box models such as deep neural networks (NNs). Nevertheless, these methods predominantly explain outputs in termsof inputs, disregarding the inner workings of the ML model computing those outputs. We present Argflow, a toolkit enabling thegeneration of a variety of ‘deep’ argumentative explanations (DAXs)for outputs of NNs on classification tasks.
AU  - Dejl,A
AU  - He,P
AU  - Mangal,P
AU  - Mohsin,H
AU  - Surdu,B
AU  - Voinea,E
AU  - Albini,E
AU  - Lertvittayakumjorn,P
AU  - Rago,A
AU  - Toni,F
EP  - 1763
PB  - ACM
PY  - 2021///
SP  - 1761
TI  - Argflow: a toolkit for deep argumentative explanations for neural networks.
UR  - https://dl.acm.org/doi/proceedings/10.5555/3463952?tocHeading=heading1
ER  - 

Download