Automated PrOduct GEneration and Enrichment (APOGEE)

Creating information products to answer Tell Me About questions requires the ability to identify key pieces of information relevant to a complex set of information requirements. Complicating matters, these key pieces of information exist in multiple modalities scattered across data stores, buried in huge volumes of data. This results in the current predicament analysts find themselves; information retrieval and management consumes huge amounts of time that could be better spent performing analysis. The persistent growth in data accumulation rates will only increase the amount of time spent on these tasks without a significant advance in automated solutions for information product generation. We present Phase II of the Automated PrOduct GEneration and Enrichment (APOGEE) effort. APOGEE automates the creation of information products; learning the creation process by example. APOGEE can uses automatically constructed content models of fine-grained information requirements to retrieve mix-modal data for inclusion in products. This data is automatically filtered to eliminate redundancy and fused into an information product. APOGEEs mixed-initiative user interface helps analysts rapidly produce finished information products in significantly less time than possible with existing tools and methodologies. This allows analyst to shift efforts from data management to analytic tasks.