Arguments using ontological and causal knowledge
This work addresses the challenge of causal explanation in complex systems for domains like disaster analysis, but it appears incremental as it builds on existing argumentation and causal modeling approaches.
The paper tackles the problem of reasoning about causes through argumentation by developing a system that uses causal and ontological links to provide candidate explanations for facts, applied to a case study of the 2010 Xynthia storm in France to analyze high casualties.
We investigate an approach to reasoning about causes through argumentation. We consider a causal model for a physical system, and look for arguments about facts. Some arguments are meant to provide explanations of facts whereas some challenge these explanations and so on. At the root of argumentation here, are causal links ({A_1, ... ,A_n} causes B) and ontological links (o_1 is_a o_2). We present a system that provides a candidate explanation ({A_1, ... ,A_n} explains {B_1, ... ,B_m}) by resorting to an underlying causal link substantiated with appropriate ontological links. Argumentation is then at work from these various explaining links. A case study is developed: a severe storm Xynthia that devastated part of France in 2010, with an unaccountably high number of casualties.