FROM: U.S. DEPARTMENT OF DEFENSE ARMED WITH SCIENCE
DEEP EXPLORATION AND FILTERING TEXT
Written on JUNE 8, 2012 AT 7:10 AM by JTOZER
Are You Inferring What I think You’re Inferring?
Much of the operationally-relevant information relied on in support of DoD missions may be implicit rather than explicitly expressed, and in many cases, information is deliberately obfuscated and important activities and objects are only indirectly referenced.”
In short, sometimes the meaning in messages just isn’t clear. Ironic, isn’t it?
That can be a problem, though, especially on the ground where accurate and timely intelligence can affect the success or failure of a mission.
Through various and sundry means, DoD collects vast sets of data in the form of messages, documents, notes and the like, both on and off the battlefield. Thoroughly and efficiently processing this data to extract valuable content is a challenge based on volume alone, but the problem is magnified when important information within those files is deliberately masked by its authors.
So, what is there to do when you have commanders and warfighters on the front line depending on analysts to help them build informed plans?
Why, you use technology, of course.
DARPA is developing a new type of automated, deep natural-language understanding technology which they say may hold a solution for more efficiently processing text information. A mumbo-jumbo decomplicator?
Go on…
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. A “just the facts” approach is more effective than the “the give us the whole story” angle,
so to speak. Also, it’s fun to talk like a 1940s detective.
But how do you do that? Not the detective talk, sweetheart, I mean the dialing-it-down. Getting to the root of the story. The meat and potatoes of the whole shebang (okay, I’ll stop).
In short, DEFT. At length…it makes more sense.
DARPA created the Deep Exploration and Filtering of Text (DEFT) program to harness the power of language. Sophisticated artificial intelligence of this nature has the potential to enable defense analysts to efficiently investigate documents so they can discover implicitly expressed, actionable information contained within them.
Letting the technology do the dirty work, eh? (last one I swear).
Actually that’s a smart idea. But that implies that the system will be capable of understanding the thought that goes behind human communication, right? How is an AI going to know what we mean by our vague platitudes or double entendres? Will it know what I mean when I type LOL?
“DEFT is attempting to create technology to make reliable inferences based on basic text,” said Bonnie Dorr, DARPA program manager for DEFT. “We want the ability to mitigate ambiguity in text by stripping away filters that can cloud meaning and by rejecting false information. To be successful, the technology needs to look beyond what is explicitly expressed in text to infer what is actually meant.”
The development of an automated solution may rely on contributions from the linguistics and computer science fields in the areas of artificial intelligence, computational linguistics, machine learning, natural-language understanding, discourse and dialogue analysis, and others.
They could have used this in Star Trek, you know. Something complicated would happen and then one of the characters would have to sum it up in a simple metaphor. With DEFT, they could have taken all those pithy one-liners out. Imagine all the time and energy they could have saved while the warp core breached. Again.
DEFT will build on existing DARPA programs and ongoing academic re
search into deep language understanding and artificial intelligence to address remaining capability gaps related to inference, causal relationships and anomaly detection.
“Much of the basic research needed for DEFT has been accomplished, but now has to be scaled, applied and integrated through the development of new technology,” Dorr said.
As information is processed, DEFT also aims to integrate individual facts into large domain models for assessment, planning and prediction. If successful, DEFT will allow analysts to move from limited, linear processing of insurmountable quantities of data to a nuanced, strategic exploration of available information.
So, by reading between the overly-complicated lines, DEFT might actually be able to glean useful information from what would otherwise be muddled and confusing messages. I wonder if they can turn this technology into a teenage-text filter so I can weed through the bizarre pseudo-cavemen texts I get from my cousin. Then I’ll finally know what “IDK, TTYL8R” means.
