Moving from data to text using causal statements in explanatory narratives

Data-to-text natural language generation techniques do not currently impart deep meaning in their output and leave it to an expert user to draw causal inferences. Frequently, the expert is adding meaning that would be present in data sources that could be made available to the NLG system. As the system is intended to convey as much information as possible, it seems counterintuitive to require the user to add meaning that could already have been included in the systems output. In this paper, we introduce our concept of using a reasoning engine to draw causal inferences about the data and then expressing them in an explanatory narrative.