Citation

BibTex format

@inproceedings{Rago:2022:kr.2022/52,
author = {Rago, A and Baroni, P and Toni, F},
doi = {kr.2022/52},
pages = {505--509},
publisher = {IJCAI Organisation},
title = {Explaining causal models with argumentation: the case of bi-variate reinforcement},
url = {http://dx.doi.org/10.24963/kr.2022/52},
year = {2022}
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - Causal models are playing an increasingly important role inmachine learning, particularly in the realm of explainable AI.We introduce a conceptualisation for generating argumenta-tion frameworks (AFs) from causal models for the purposeof forging explanations for the models’ outputs. The concep-tualisation is based on reinterpreting desirable properties ofsemantics of AFs as explanation moulds, which are meansfor characterising the relations in the causal model argumen-tatively. We demonstrate our methodology by reinterpretingthe property of bi-variate reinforcement as an explanationmould to forge bipolar AFs as explanations for the outputs ofcausal models. We perform a theoretical evaluation of theseargumentative explanations, examining whether they satisfy arange of desirable explanatory and argumentative propertie
AU - Rago,A
AU - Baroni,P
AU - Toni,F
DO - kr.2022/52
EP - 509
PB - IJCAI Organisation
PY - 2022///
SN - 2334-1033
SP - 505
TI - Explaining causal models with argumentation: the case of bi-variate reinforcement
UR - http://dx.doi.org/10.24963/kr.2022/52
UR - https://proceedings.kr.org/2022/52/
UR - http://hdl.handle.net/10044/1/97078
ER -

Contact us

Artificial Intelligence Network
South Kensington Campus
Imperial College London
SW7 2AZ

To reach the elected speaker of the network, Dr Rossella Arcucci, please contact:

ai-speaker@imperial.ac.uk

To reach the network manager, Diana O'Malley - including to join the network - please contact:

ai-net-manager@imperial.ac.uk