Abstract
SMT solvers can be used efficiently to search for optimal paths across multiple graphs when optimising for certain resources. In the medical context, these graphs can represent treatment plans for chronic conditions where the optimal paths across all plans under consideration are the ones which minimize adverse drug interactions. The SMT solvers, however, work as a black-box model and there is a need to justify the optimal plans in a human-friendly way. We aim to fulfill this need by proposing explanatory dialogue protocols based on computational argumentation to increase the understanding and trust of humans interacting with the system. The protocols provide supporting reasons for nodes in a path and also allow counter reasons for the nodes not in the graph, highlighting any potential adverse interactions during the dialogue.
Original language | English |
---|---|
Title of host publication | Rules and Reasoning |
Subtitle of host publication | 4th International Joint Conference, RuleML+RR 2020, Oslo, Norway, June 29–July 1, 2020, Proceedings |
Editors | Victor Gutiérrez Basulto, Tomáš Kliegr, Ahmet Soylu, Martin Giese, Dumitru Roman |
Place of Publication | Cham |
Publisher | Springer |
Pages | 97-111 |
Number of pages | 15 |
ISBN (Electronic) | 9783030579777 |
ISBN (Print) | 9783030579760 |
DOIs | |
Publication status | Published - 2020 |
Event | 4th International Joint Conference on Rules and Reasoning (RCUL+RR 2020) - Online, Oslo, Norway Duration: 29 Jun 2020 → 1 Jul 2020 Conference number: 4 https://2020.declarativeai.net/ |
Publication series
Name | Lecture Notes in Computer Science (Programming and Software Engineering) |
---|---|
Publisher | Springer |
Volume | 12173 LNCS |
ISSN (Print) | 0302-9743 |
Conference
Conference | 4th International Joint Conference on Rules and Reasoning (RCUL+RR 2020) |
---|---|
Abbreviated title | RCUL+RR 2020 |
Country/Territory | Norway |
City | Oslo |
Period | 29/06/20 → 1/07/20 |
Internet address |
Keywords
- Explanations
- Dialogues games
- Argumentation
- SMT solvers