Homeland security library gets more searchable
Software from Teragram uses linguistic and semantic analysis to automatically categorize PDF, video and audio documents by their meaning.
Students and faculty at the school’s Center for Homeland Defense and Security use the Homeland Security Digital Library (HSDL) as a primary research tool.
Homeland security policy-makers at the federal, state and local levels also use HSDL to find strategy, policy and research documents.
Teragram makes software that yields more accurate and comprehensive search results, said Yves Schabes, the company’s president. The software uses linguistic and semantic analysis to automatically categorize PDF, video and audio documents by their meaning.
The software searches the library’s holdings by full text, metadata and metadata-determined relevancy, Schabes said.
Teragram’s rule-based models handle taxonomies, which show the correlation among terms that a community of practice uses. Taxonomies are essential for indexing large numbers of documents.
Teragram consistently assigns taxonomy designations to new data, making it easier for the library’s managers to keep pace with the large number of new documents they add daily, Schabes said. The software also lets managers add new terminology or broaden or narrow search rules as needed.
“Teragram’s technology has helped bring HSDL to where it is today,” said Thomas Mastre, project manager for HSDL, in a statement.
The library contains a large number of categories that include Law and Justice, Borders and Immigration, Infrastructure Protection, Terrorism and Society, Weapons and Weapons Systems, Emergency Management, and Public Health, according to the statement.
The Homeland Security Department’s Office of Grants and Training sponsors the library, which started operating in September 2005. The company started working with the library in fall 2004.
NEXT STORY: Information becomes a weapon