RT Journal Article
T1 Information-seeking dialogue for explainable artificial intelligence: modelling and analytics
A1 Stepin, Ilia
A1 Budzynska, Katarzyna
A1 Catalá Bolós, Alejandro
A1 Pereira Fariña, Martín
A1 Alonso Moral, José María
K1 Explainable Artificial Intelligence
K1 Information-seeking dialogue game
K1 Explanation locutions
K1 Counterfactual explanation
K1 Process mining analytics
K1 Argument analytics
AB Explainable artificial intelligence has become a vitally important research field aiming, among other tasks, to justify predictions made by intelligent classifiers automatically learned from data. Importantly, efficiency of automated explanations may be undermined if the end user does not have sufficient domain knowledge or lacks information about the data used for training. To address the issue of effective explanation communication, we propose a novel information-seeking explanatory dialogue game following the most recent requirements to automatically generated explanations. Further, we generalise our dialogue model in form of an explanatory dialogue grammar which makes it applicable to interpretable rule-based classifiers that are enhanced with the capability to provide textual explanations. Finally, we carry out an exploratory user study to validate the corresponding dialogue protocol and analyse the experimental results using insights from process mining and argument analytics. A high number of requests for alternative explanations testifies the need for ensuring diversity in the context of automated explanations.
PB SAGE Publications
SN 1946-2166
YR 2024
FD 2024-03-18
LK https://hdl.handle.net/10347/40939
UL https://hdl.handle.net/10347/40939
LA eng
NO Stepin I, Budzynska K, Catala A, Pereira-Fariña M, Alonso-Moral JM. Information-seeking dialogue for explainable artificial intelligence: Modelling and analytics. Argument & Computation. 2023;15(1):49-107. doi:10.3233/AAC-220011
DS Minerva
RD 29 abr 2026