Publications

Qurat-ul-ain Shaheen, Katarzyna Budzynska,and Carles Sierra. An Explanation-oriented Inquiry Dialogue Game for Expert Collaborative Recommendations. Argument and Computation, 15(3), 355–390. (2024, March). IOS Press. DOI: link.

This work presents a requirement analysis for collaborative dialogues among medical experts and an inquiry dialogue game based on this analysis for incorporating explainability into multiagent system design. The game allows experts with different knowledge bases to collaboratively make recommendations while generating rich traces of the reasoning process through combining explanation-based illocutionary forces in an inquiry dialogue. The dialogue game was implemented as a prototype web-application and evaluated against the specification through a formative user study. The user study confirms that the dialogue game meets the needs for collaboration among medical experts. It also provides insights on the real-life value of dialogue-based communication tools for the medical community.

Qurat-ul-ain Shaheen, Alice Toniolo, and Juliana Bowles. Dialogue Games for Explaining Medication Choices. RuleML+RR 2020: International Joint Conference on Rules and Reasoning. Lecture Notes in Computer Science, 12173 LNCS, 97–111. (2020, June). Springer, Cham. DOI: link.

Satisfiability Modulo Theories (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. This work presents two 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.

Qurat-ul-ain Shaheen, Alice Toniolo, and Juliana Bowles. Argumentation-Based Explanations of Multimorbidity Treatment Plans. PRIMA 2020: Principles and Practice of Multi-Agent Systems. Lecture Notes in Computer Science, 12568 LNAI, 394–402. (2021, November). Springer, Cham. DOI: link

This work presents a computational argumentation model to explain the optimal treatment plans recommended by an SMT solver for multimorbid patients. The resulting framework can be queried to obtain supporting reasons for nodes on a path following a model of argumentation schemes. The modelling approach is generic and can be used for justifying similar sequences.

Martijn Demollin, Qurat-ul-ain Shaheen, Katarzyna Budzynska,and Carles Sierra. Argumentation Theoretical Frameworks for Explainable Artificial Intelligence. 2nd Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence, 44–49. (2020, November). ACM. URL: link

This paper discusses four major argumentation theoretical frameworks with respect to their use in support of explainable artificial intelligence (XAI). We consider these frameworks as useful tools for both system-centred and user-centred XAI. The former is concerned with the generation of explanations for decisions taken by AI systems, while the latter is concerned with the way explanations are given to users and received by them.