Explaining the outcome of knowledge-based systems

A discussion-based approach

Martinus Wigbertus Antonius Caminada, Mikolaj Podlaszewski, Matthew James Green

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Many inferences made in everyday life are only valid in the absence of explicit counter information. This has led to the development of nonmonotonic logics. The kind of reasoning performed by these logics can be difficult to explain to the average end-user of a knowledge based system that implements them. Although the system can still give advice, it is hard for the user to assess the rationale behind this advice. In this paper we propose an argumentation approach that enables the advice to be assessed through an interactive dialogue with the system much like the discussion one might have with a colleague. The aim of thie dialogue is for the system to convince the user that the advice is well-founded.
Original languageEnglish
Title of host publicationProceedings of the Society for the Study of Artificial Intelligence and the Simulation of Behaviour 2013
PublisherAISB
Number of pages4
Publication statusPublished - 2013
EventDo-Form: Enabling Domain Experts to use Formalised Reasoning - Exeter, United Kingdom
Duration: 3 Apr 20135 Apr 2013

Conference

ConferenceDo-Form: Enabling Domain Experts to use Formalised Reasoning
CountryUnited Kingdom
CityExeter
Period3/04/135/04/13

Fingerprint

Knowledge based systems

Cite this

Caminada, M. W. A., Podlaszewski, M., & Green, M. J. (2013). Explaining the outcome of knowledge-based systems: A discussion-based approach. In Proceedings of the Society for the Study of Artificial Intelligence and the Simulation of Behaviour 2013 AISB.

Explaining the outcome of knowledge-based systems : A discussion-based approach. / Caminada, Martinus Wigbertus Antonius; Podlaszewski, Mikolaj; Green, Matthew James.

Proceedings of the Society for the Study of Artificial Intelligence and the Simulation of Behaviour 2013. AISB, 2013.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Caminada, MWA, Podlaszewski, M & Green, MJ 2013, Explaining the outcome of knowledge-based systems: A discussion-based approach. in Proceedings of the Society for the Study of Artificial Intelligence and the Simulation of Behaviour 2013. AISB, Do-Form: Enabling Domain Experts to use Formalised Reasoning, Exeter, United Kingdom, 3/04/13.
Caminada MWA, Podlaszewski M, Green MJ. Explaining the outcome of knowledge-based systems: A discussion-based approach. In Proceedings of the Society for the Study of Artificial Intelligence and the Simulation of Behaviour 2013. AISB. 2013
Caminada, Martinus Wigbertus Antonius ; Podlaszewski, Mikolaj ; Green, Matthew James. / Explaining the outcome of knowledge-based systems : A discussion-based approach. Proceedings of the Society for the Study of Artificial Intelligence and the Simulation of Behaviour 2013. AISB, 2013.
@inproceedings{3c66c7dc62d04588a40260e0fedb6a2d,
title = "Explaining the outcome of knowledge-based systems: A discussion-based approach",
abstract = "Many inferences made in everyday life are only valid in the absence of explicit counter information. This has led to the development of nonmonotonic logics. The kind of reasoning performed by these logics can be difficult to explain to the average end-user of a knowledge based system that implements them. Although the system can still give advice, it is hard for the user to assess the rationale behind this advice. In this paper we propose an argumentation approach that enables the advice to be assessed through an interactive dialogue with the system much like the discussion one might have with a colleague. The aim of thie dialogue is for the system to convince the user that the advice is well-founded.",
author = "Caminada, {Martinus Wigbertus Antonius} and Mikolaj Podlaszewski and Green, {Matthew James}",
note = "This work has been supported by the National Research Fund, Luxembourg (LAAMIcomp project) and by the Engineering and Physical Sciences Research Council (EPSRC, UK), grant ref. EP/J012084/1 (SAsSy project).",
year = "2013",
language = "English",
booktitle = "Proceedings of the Society for the Study of Artificial Intelligence and the Simulation of Behaviour 2013",
publisher = "AISB",

}

TY - GEN

T1 - Explaining the outcome of knowledge-based systems

T2 - A discussion-based approach

AU - Caminada, Martinus Wigbertus Antonius

AU - Podlaszewski, Mikolaj

AU - Green, Matthew James

N1 - This work has been supported by the National Research Fund, Luxembourg (LAAMIcomp project) and by the Engineering and Physical Sciences Research Council (EPSRC, UK), grant ref. EP/J012084/1 (SAsSy project).

PY - 2013

Y1 - 2013

N2 - Many inferences made in everyday life are only valid in the absence of explicit counter information. This has led to the development of nonmonotonic logics. The kind of reasoning performed by these logics can be difficult to explain to the average end-user of a knowledge based system that implements them. Although the system can still give advice, it is hard for the user to assess the rationale behind this advice. In this paper we propose an argumentation approach that enables the advice to be assessed through an interactive dialogue with the system much like the discussion one might have with a colleague. The aim of thie dialogue is for the system to convince the user that the advice is well-founded.

AB - Many inferences made in everyday life are only valid in the absence of explicit counter information. This has led to the development of nonmonotonic logics. The kind of reasoning performed by these logics can be difficult to explain to the average end-user of a knowledge based system that implements them. Although the system can still give advice, it is hard for the user to assess the rationale behind this advice. In this paper we propose an argumentation approach that enables the advice to be assessed through an interactive dialogue with the system much like the discussion one might have with a colleague. The aim of thie dialogue is for the system to convince the user that the advice is well-founded.

M3 - Conference contribution

BT - Proceedings of the Society for the Study of Artificial Intelligence and the Simulation of Behaviour 2013

PB - AISB

ER -