Explainable AI through the Learning of Arguments

Jonas Bei; David Pomerenke; Lukas Schreiner; Sepideh Sharbaf; Pieter Collins; Nico Roos

Explainable AI through the Learning of Arguments

Jonas Bei, David Pomerenke, Lukas Schreiner, Sepideh Sharbaf, Pieter Collins, Nico Roos^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

31 Downloads (Pure)

Abstract

earning arguments is highly relevant to the field of explainable artificial intelligence. It is a family of symbolic machine learning techniques that is particularly human-interpretable. These techniques learn a set of arguments as an intermediate representation. Arguments are small rules with exceptions that can be chained to larger arguments for making predictions or decisions.

We investigate the learning of arguments, specifically the learning of arguments from a ‘case model’ proposed by Verheij [34]. The case model in Verheij’s approach are cases or scenarios in a legal setting. The number of cases in a case model are relatively low. Here, we investigate whether Verheij’s approach can be used for learning arguments from other types of data sets with a much larger number of instances. We compare the learning of arguments from a case model with the HeRO algorithm [15] and learning a decision tree.

Original language	English
Title of host publication	Proceedings of BNAIC/BeneLearn 2021
Subtitle of host publication	33rd Benelux Conference on Artificial Intelligence and the 30th Belgian Dutch Conference on Machine Learning BNAIC/BENELEARN
Pages	241-255
Number of pages	15
Publication status	Published - 2021
Event	33rd Benelux Conference on Artificial Intelligence and 30th Belgian-Dutch Conference on Machine Learning - Belval, Esch-sur-Alzette, Luxembourg Duration: 10 Nov 2021 → 12 Nov 2021 Conference number: 33 https://bnaic2021.uni.lu/

Conference

Conference	33rd Benelux Conference on Artificial Intelligence and 30th Belgian-Dutch Conference on Machine Learning
Abbreviated title	BNAIC/BeneLearn 2021
Country/Territory	Luxembourg
City	Belval, Esch-sur-Alzette
Period	10/11/21 → 12/11/21
Internet address	https://bnaic2021.uni.lu/

Keywords

Explainable AI
Argumentation
Learning Arguments
Data Mining

Access to Document

Full text Final published version, 214 KBLicence: Taverne

Cite this

@inproceedings{1c0d96d73d02412a804a5e9b0e8230f5,

title = "Explainable AI through the Learning of Arguments",

abstract = "earning arguments is highly relevant to the field of explainable artificial intelligence. It is a family of symbolic machine learning techniques that is particularly human-interpretable. These techniques learn a set of arguments as an intermediate representation. Arguments are small rules with exceptions that can be chained to larger arguments for making predictions or decisions.We investigate the learning of arguments, specifically the learning of arguments from a {\textquoteleft}case model{\textquoteright} proposed by Verheij [34]. The case model in Verheij{\textquoteright}s approach are cases or scenarios in a legal setting. The number of cases in a case model are relatively low. Here, we investigate whether Verheij{\textquoteright}s approach can be used for learning arguments from other types of data sets with a much larger number of instances. We compare the learning of arguments from a case model with the HeRO algorithm [15] and learning a decision tree.",

keywords = "Explainable AI, Argumentation, Learning Arguments, Data Mining",

author = "Jonas Bei and David Pomerenke and Lukas Schreiner and Sepideh Sharbaf and Pieter Collins and Nico Roos",

year = "2021",

language = "English",

pages = "241--255",

booktitle = "Proceedings of BNAIC/BeneLearn 2021",

note = "33rd Benelux Conference on Artificial Intelligence and 30th Belgian-Dutch Conference on Machine Learning, BNAIC/BeneLearn 2021 ; Conference date: 10-11-2021 Through 12-11-2021",

url = "https://bnaic2021.uni.lu/",

}

Bei, J, Pomerenke, D, Schreiner, L, Sharbaf, S, Collins, P & Roos, N 2021, Explainable AI through the Learning of Arguments. in Proceedings of BNAIC/BeneLearn 2021: 33rd Benelux Conference on Artificial Intelligence and the 30th Belgian Dutch Conference on Machine Learning BNAIC/BENELEARN. pp. 241-255, 33rd Benelux Conference on Artificial Intelligence and 30th Belgian-Dutch Conference on Machine Learning, Belval, Esch-sur-Alzette, Luxembourg, 10/11/21.

Explainable AI through the Learning of Arguments. / Bei, Jonas; Pomerenke, David; Schreiner, Lukas et al.
Proceedings of BNAIC/BeneLearn 2021: 33rd Benelux Conference on Artificial Intelligence and the 30th Belgian Dutch Conference on Machine Learning BNAIC/BENELEARN. 2021. p. 241-255.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

TY - GEN

T1 - Explainable AI through the Learning of Arguments

AU - Bei, Jonas

AU - Pomerenke, David

AU - Schreiner, Lukas

AU - Sharbaf, Sepideh

AU - Collins, Pieter

AU - Roos, Nico

N1 - Conference code: 33

PY - 2021

Y1 - 2021

N2 - earning arguments is highly relevant to the field of explainable artificial intelligence. It is a family of symbolic machine learning techniques that is particularly human-interpretable. These techniques learn a set of arguments as an intermediate representation. Arguments are small rules with exceptions that can be chained to larger arguments for making predictions or decisions.We investigate the learning of arguments, specifically the learning of arguments from a ‘case model’ proposed by Verheij [34]. The case model in Verheij’s approach are cases or scenarios in a legal setting. The number of cases in a case model are relatively low. Here, we investigate whether Verheij’s approach can be used for learning arguments from other types of data sets with a much larger number of instances. We compare the learning of arguments from a case model with the HeRO algorithm [15] and learning a decision tree.

AB - earning arguments is highly relevant to the field of explainable artificial intelligence. It is a family of symbolic machine learning techniques that is particularly human-interpretable. These techniques learn a set of arguments as an intermediate representation. Arguments are small rules with exceptions that can be chained to larger arguments for making predictions or decisions.We investigate the learning of arguments, specifically the learning of arguments from a ‘case model’ proposed by Verheij [34]. The case model in Verheij’s approach are cases or scenarios in a legal setting. The number of cases in a case model are relatively low. Here, we investigate whether Verheij’s approach can be used for learning arguments from other types of data sets with a much larger number of instances. We compare the learning of arguments from a case model with the HeRO algorithm [15] and learning a decision tree.

KW - Explainable AI

KW - Argumentation

KW - Learning Arguments

KW - Data Mining

M3 - Conference article in proceeding

SP - 241

EP - 255

BT - Proceedings of BNAIC/BeneLearn 2021

T2 - 33rd Benelux Conference on Artificial Intelligence and 30th Belgian-Dutch Conference on Machine Learning

Y2 - 10 November 2021 through 12 November 2021

ER -