Semantic Analysis of Military Relevant Texts for Intelligence Purposes

摘要

The current deployments of the German Federal Armed Forces make it necessary to analyze large quantities of intelligence reports and other documents written in different languages. Natural language processing techniques (NLP) can be applied to efficiently handle these tasks. The ZENON project makes use of an information extraction approach for the (partial) content analysis of English HUMINT reports. It has been extended to do multilingual information extraction (i.e., processing Dari and Tajik texts). This paper focuses on the improvement of ZENON's English semantic analysis. To extend the system's coverage when performing content analysis the authors used a semantic role labeling approach. The paper describes the ZENON system and its information extraction functions, the semantic role labeling approach, and the architecture of the implemented application. The presentation includes briefing charts.