DARPA system to blend AI, machine learning to understand mountain of text
From the post:
The Defense Advanced Research Projects Agency (DARPA) will next this month detail the union of advanced technologies from artificial intelligence, computational linguistics, machine learning, natural-language fields it hopes to bring together to build an automated system that will let analysts and others better grasp meanings from large volumes of text documents.
From DARPA: “Automated, deep natural-language understanding technology may hold a solution for more efficiently processing text information. When processed at its most basic level without ingrained cultural filters, language offers the key to understanding connections in text that might not be readily apparent to humans. Sophisticated artificial intelligence of this nature has the potential to enable defense analysts to efficiently investigate orders of magnitude more documents so they can discover implicitly expressed, actionable information contained within them.”
DARPA is holding a proposers day, May 16, 2012 in Arlington, VA, on the Deep Exploration and Filtering of Text (DEFT) project.
I won’t be attending but am interested in what you learn about the project.
What has me curious is that assuming DEFT is successful, how do they intend to capture the insights of analysts who describe the data and their conclusions differently? Particularly over time or from the perspective of different intelligence agencies? Or document the trails a particular analyst has followed through a mountain of data? Seems like those would be important issues as well.
Issues that are uniquely suited for subject-centric approaches like topic maps.