Fusion Rules for Context-Dependent Aggregation of Structured News Reports

A NewsFusion System is a logic-based system for merging heterogeneous structured news reports. Structured news reports are XML documents, where the textentries are restricted to individual words or simple phrases, such as names and domain-specific terminology, and numbers and units. We assume structured news reports do not require natural language processing. In previous papers, we have presented aspects of a logic-based framework for merging structured news reports based on fusion rules. Fusion rules are a form of scripting language that define how structured news reports should be merged. The antecedent of a fusion rule is a call to investigate the information in the structured news reports and the background knowledge, and the consequent of a fusion rule is a formula specifying an action to be undertaken to form a merged report. It is expected that a set of fusion rules is defined for any given application. In this paper, we present a framework for aggregation predicates that can be used in fusion rules for context-dependent aggregation of structured news reports. We also present a case study that uses aggregation predicates to merge weather reports that have been obtained from a selection of websites.