Citation

BibTex format

@article{Lertvittayakumjorn:2023:10.3233/aac-220004,
author = {Lertvittayakumjorn, P and Toni, F},
doi = {10.3233/aac-220004},
journal = {Argument and Computation},
pages = {163--234},
title = {Argumentative explanations for pattern-based text classifiers},
url = {http://dx.doi.org/10.3233/aac-220004},
volume = {14},
year = {2023}
}

RIS format (EndNote, RefMan)

TY  - JOUR
AB - Recent works in Explainable AI mostly address the transparency issue of black-box models or create explanations for any kind of models (i.e., they are model-agnostic), while leaving explanations of interpretable models largely underexplored. In this paper, we fill this gap by focusing on explanations for a specific interpretable model, namely pattern-based logistic regression (PLR) for binary text classification. We do so because, albeit interpretable, PLR is challenging when it comes to explanations. In particular, we found that a standard way to extract explanations from this model does not consider relations among the features, making the explanations hardly plausible to humans. Hence, we propose AXPLR, a novel explanation method using (forms of) computational argumentation to generate explanations (for outputs computed by PLR) which unearth model agreements and disagreements among the features. Specifically, we use computational argumentation as follows: we see features (patterns) in PLR as arguments in a form of quantified bipolar argumentation frameworks (QBAFs) and extract attacks and supports between arguments based on specificity of the arguments; we understand logistic regression as a gradual semantics for these QBAFs, used to determine the arguments’ dialectic strength; and we study standard properties of gradual semantics for QBAFs in the context of our argumentative re-interpretation of PLR, sanctioning its suitability for explanatory purposes. We then show how to extract intuitive explanations (for outputs computed by PLR) from the constructed QBAFs. Finally, we conduct an empirical evaluation and two experiments in the context of human-AI collaboration to demonstrate the advantages of our resulting AXPLR method.
AU - Lertvittayakumjorn,P
AU - Toni,F
DO - 10.3233/aac-220004
EP - 234
PY - 2023///
SN - 1946-2174
SP - 163
TI - Argumentative explanations for pattern-based text classifiers
T2 - Argument and Computation
UR - http://dx.doi.org/10.3233/aac-220004
UR - https://content.iospress.com/articles/argument-and-computation/aac220004
UR - http://hdl.handle.net/10044/1/104407
VL - 14
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