Constructing Bayesian Network Graphs from Labeled Arguments

Bayesian networks (BNs) are powerful tools that are well-suited for reasoning about the uncertain consequences that can be inferred from evidence. Domain experts, however, typically do not have the expertise to construct BNs and instead resort to using other tools such as argument diagrams and mind maps. Recently, we proposed a structured approach to construct a BN graph from arguments annotated with causality information. As argumentative inferences may not be causal, we generalize this approach to include other types of inferences in this paper. Moreover, we prove a number of formal properties of the generalized approach and identify assumptions under which the construction of an initial BN graph can be fully automated.

[1]  Linda C. van der Gaag,et al.  Building Bayesian Networks through Ontologies , 2002, ECAI.

[2]  Henry Prakken.  Probabilistic Strength of Arguments with Structure , 2018, KR.

[3]  Anthony Hunter,et al.  On Partial Information and Contradictions in Probabilistic Abstract Argumentation , 2016, KR.

[4]  Anthony Hunter,et al.  A probabilistic approach to modelling uncertain logical arguments , 2013, Int. J. Approx. Reason..

[5]  Finn V. Jensen,et al.  Bayesian Networks and Decision Graphs , 2001, Statistics for Engineering and Information Science.

[6]  Tjitze Rienstra.  Towards a Probabilistic Dung-style Argumentation System , 2012, AT.

[7]  Simon Buckingham Shum,et al.  The Roots of Computer Supported Argument Visualization , 2003, Visualizing Argumentation.

[8]  Henry Prakken,et al.  On logical specifications of the Argument Interchange Format , 2013, J. Log. Comput..

[9]  Judea Pearl,et al.  Embracing Causality in Default Reasoning , 1988, Artif. Intell..

[10]  Jeroen Keppens.  On modelling non-probabilistic uncertainty in the likelihood ratio approach to evidential reasoning , 2014, Artificial Intelligence and Law.

[11]  Henry Prakken,et al.  Exploiting Causality in Constructing Bayesian Network Graphs from Legal Arguments , 2018, JURIX.

[12]  Floris Bex.  An integrated theory of causal stories and evidential arguments , 2015, ICAIL.

[13]  Norman Fenton,et al.  Risk Assessment and Decision Analysis with Bayesian Networks , 2012 .

[14]  Linda C. van der Gaag,et al.  Experiences with Modelling Issues in Building Probabilistic Networks , 2002, EKAW.

[15]  Henry Prakken,et al.  Explaining Bayesian Networks Using Argumentation , 2015, ECSQARU.

[16]  Floris Bex,et al.  From Arguments to Constraints on a Bayesian Network , 2016, COMMA.

[17]  Henry Prakken,et al.  Supporting Discussions About Forensic Bayesian Networks Using Argumentation , 2019, ICAIL.

[18]  Jeroen Keppens.  Argument diagram extraction from evidential Bayesian networks , 2012, Artificial Intelligence and Law.

[19]  Daniele Theseider Dupré,et al.  Adcuctive Reasoning with Abstraction Axioms , 1992, ECAI Workshop on Knowledge Representation and Reasoning.