BOSTON FUSION CORP — Department of Defense SBIR Phase I: Typical search technology ignores the intended usage of documentsmissing the opportunity t

Description

Typical search technology ignores the intended usage of documentsmissing the opportunity to tailor prioritization and anticipate supplemental materials. Semantic targetingtailoring content to the user"s predicted interests or needsshows promise for improving analytical workflows. What is needed is a sophisticated approach to incorporating the user as part of the data model, leveraging the data, behaviors and interests of the user, and of prior analysts. Because analyst turnover is rampant, embedding legacy knowledge into the data model is critical for capturing guidance of trained analysts and helping new analysts conquer steep learning curves. We will assess the state-of-the-art, develop a system concept, and build a prototype to automatically adapt search using analysts"roles. We will learn how role-specific individuals select and navigate content, follow leads, and identify relevant data in complex, multi-step tasking to accomplish this vision. To minimize the training data burden, we rely on minimally-invasive approaches that discover the roles, semantic content, and semantic connections. We will leverage and extend work in probabilistic topic modeling to include the role information and complex operational tasking. We will leverage our experience on the ONR-sponsored Mission-Focused Autonomy program to develop a plan to transition STARTER to an intelligence analysis environment.