The Intelligence Advanced Research Projects Activity has chosen four teams led by a Raytheon (NYSE: RTN) subsidiary and three universities to perform research and development work on a system to retrieve data from cross-lingual and multitopic sources.
Raytheon BBN Technologies, Brown University, Johns Hopkins University and the University of Southern California Information Sciences Institute secured research contracts under IARPA's Better Extraction from Text Towards Enhanced Retrieval program, the Office of the Director of National Intelligence said Wednesday.
IAPA intends for the four teams to employ deep learning approaches for knowledge discovery and complex semantic tools for information retrieval.
“The system we envision will exploit various levels of information extraction to improve cross-lingual information retrieval across large unstructured, multilingual document sets using novel methods to enhance the user’s experience for both document triage and discovery,” said Carl Rubino, an IARPA program manager.
“To stimulate competitive methods, we will score the performer teams against a baseline model the test and evaluation team developed," Rubino added.
ODNI noted the National Institute for Standards and Technology and nonprofit company Mitre will conduct assessments of data extraction and retrieval platforms for as many as five languages per team.