Textual Inference for Grounding Events in Space (TIGRESS)

ABSTRACT: The goal of the proposed work is to develop a robust spatial reasoning capacity that can provide analysts in both national defense and business environments with operational-quality spatial information about events in unstructured texts from any domain. In order to achieve this goal, we plan to combine an open-domain and customizable event extraction framework with a suite of components designed to acquire all of the explicit and implicit spatial information available from collections of natural language texts. In contrast with most current approaches to spatial information processing, we will create an integrated reasoning-based framework which will leverage LCC"s existing information extraction, spatial reasoning and normalization, textual entailment, and semantic parsing capabilities in order to accurately locate events for spatial visualization applications. In executing Phase I of this effort, we shall define the operational semantics for event locating, select training and testing data for conceptual representations and semantic processing, and define requirements for each module. BENEFIT: We believe there is a growing need for systems capable of providing a wide range of accurate spatial and temporal information about events from unstructured texts within multiple sectors of the U.S. government, including the Departments of Defense, Department of Homeland Security, Federal Bureau of Investigation, and the national intelligence organizations overseen by the Office of the Director of National Intelligence. We anticipate that the prototype location-tagging and spatial reasoning system being developed as part of TIGRESS will not only enhance the quality of LCC"s suites of open-domain customizable event extraction tools, but will also serve the location-tagging and spatial visualization needs of operational customers as well. Transitioning our technology into these organizations will support incident responders, incident managers, intelligence preparation of the battlefield, and event detection / response collaboration. To accomplish our objectives, we will solicit our current contacts within the Intelligence and Homeland Security communities to demonstrate and tailor this capability to their needs. For DoD customers, we will work through our strategic partners to demonstrate and integrate conceptual visualization into their current and future systems. As fully location-tagging and spatial reasoning capabilities become more robust, we expect the quality and coverage of our applications will drive demand for LCC"s products in the civilian commercial sector as well.