Towards Presenting Relevant Facts and Answers on Inconsistent and Uncertain Knowledge

In the presence of vast amount of data and their semantic representation, it is a formidable task for a human decision-maker to effectively locate the most relevant facts, identify critical conflicts, and master a big picture of the information for high quality decision making. This paper proposes a presentation framework which applies argumentation-based reasoning to present relevant facts and answers. Knowledge retrieved from a distributed semantic KB are fed into an argumentationbased reasoning engine which re-organizes the knowledge into coherent arguments, estimates the beliefs of the arguments, and analyzes the pattern of conflicts among the arguments to preliminarily determine the acceptability of these arguments for the decision-maker to review. In order to lower the decision-maker’s cognitive load, the argumentation is pruned to present only the arguments and the conflicts that most likely concern the decision-maker. This argumentation pruning algorithm can be adapted to enable a decision-maker to interact with the system and navigate through the information incrementally unfolding the argumentation constructed for the answers.

[1]  Munindar P. Singh,et al.  Trust Representation and Aggregation in a Distributed Agent System , 2006, AAAI.

[2]  Audun Jøsang,et al.  A Logic for Uncertain Probabilities , 2001, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

[3]  Elizabeth Sklar,et al.  Using argumentation to reason about trust and belief , 2012, J. Log. Comput..

[4]  Oren Etzioni,et al.  Learning First-Order Horn Clauses from Web Text , 2010, EMNLP.

[5]  A. Jøsang.  TRUST-BASED DECISION MAKING FOR ELECTRONIC TRANSACTIONS , 1999 .

[6]  Phan Minh Dung,et al.  On the Acceptability of Arguments and its Fundamental Role in Nonmonotonic Reasoning, Logic Programming and n-Person Games , 1995, Artif. Intell..

[7]  Dov M. Gabbay,et al.  A Logical Account of Formal Argumentation , 2009, Stud Logica.

[8]  John L. Pollock,et al.  Defeasible reasoning with variable degrees of justification , 2001, Artif. Intell..

[9]  Jie Yang,et al.  Sensor Fusion Using Dempster-Shafer Theory , 2002 .

[10]  Claudette Cayrol,et al.  Graduality in Argumentation , 2011, J. Artif. Intell. Res..

[11]  K. Sycara,et al.  Anytime Cognition: An information agent for emergency response , 2011 .

[12]  Gerhard Weikum,et al.  YAGO: A Large Ontology from Wikipedia and WordNet , 2008, J. Web Semant..

[13]  Alun D. Preece,et al.  Subjective logic and arguing with evidence , 2007, Artif. Intell..

[14]  Jeff Z. Pan,et al.  Querying Linked Ontological Data through Distributed Summarization , 2012, AAAI.

[15]  E. Sklar,et al.  An Argumentation Engine : ArgTrust , 2012 .