Diversity Rank-Based Summarization of Stream Texts Navy SBIR FY2012.1 Sol No.: Navy SBIR FY2012.1 Topic No.: N121-078 Topic Title: Diversity Rank-Based Summarization of Stream Texts Proposal No.: N121-078-1204 Firm: Intelligent Automation, Inc. 15400 Calhoun Drive Suite 400 Rockville, Maryland 20855 Contact: Xiong Liu Phone: (301) 294-4629 Web Site: www.i-a-i.com Abstract: Intelligent Automation, Inc. (IAI) proposes a novel Diversity rank-based Summarization Tool (DST) for extracting and updating succinct summary from streaming text. DST is a large-scale, dynamic and fast approach for maximizing the ability of intelligence analysts to analyze text-based communication to assess the ever-changing content and trend. With DST, the evolution of the target topic is tracked in real-time. The text network is constructed and updated very efficiently to enhance real-time summary updating. The importance, diversity, and novelty of content in the summary are balanced and optimized through a principled graph-regularization framework. Benefits: IAI's proposed technology can be directly applied to the military and intelligence contexts, such as domestic and international security regulations. The summary extraction and updating capabilities can help analysts understand real-time topics and forecast future trends. Our methods can provide very fast and efficient summary of text-based communication, and these tools will help analysts assess the importance and novelty of communication. In the commercial sector we anticipate that the resulting technology will have wide applications in crime identification and prevention, law enforcement, journalism, health communication, and business and economic analysis. Return