DARPA semantic program seeks to glean truth from obfuscation
In this era where disinformation, alternative facts and other falsehoods are the rule of the day, the researchers at DARPA are looking to build a mechanism that can glean some truth from the obfuscation.
DARPA says the program, called Active Interpretation of Disparate Alternatives (AIDA), looks to develop a “semantic engine” that generates alternative interpretations or meaning of real-world events, situations, and trends based on data obtained from an extensive range of channels. The program aims to create technology capable of aggregating and mapping pieces of information automatically derived from multiple media sources into a common representation or storyline, and then generating and exploring multiple theories about the true nature and implications of events, situations, and trends of interest, DARPA says. +More on Network World: DARPA plan would reinvent not-so-clever machine learning systems+
DARPA says that there are currently numerous technologies and platforms to analyze various media inputs, such as text, speech, images, videos, metadata, and other sensor inputs. “However, these analytics provide disparate outputs with semantics that are not easily combined. Using only one-best output may result in errors due to ambiguities in the input or inaccuracies in the analysis process. Also, it is often unclear which derived knowledge elements should be considered for hypotheses and which can be treated as background information,” the agency says.
“It is a challenge for those who strive to achieve and maintain an understanding of world affairs that information from each medium is often analyzed independently, without the context provided by information from other media,” said Boyan Onyshkevych, program manager in DARPA’s Information Innovation Office (I2O) in a statement. “Often, each independent analysis results in only one interpretation, with alternate interpretations eliminated due to lack of evidence even in the absence of evidence that would contradict those alternatives.”
+More on Network World: DARPA fortifies early warning system for power-grid cyber assault+
A few of the important basics of AIDA include:
- The AIDA prototype will be expected to operate in a constantly streaming data environment, where incoming information items (e.g., individual documents or images) will be handled one at a time, and will not be available to be revisited in their raw form.
- Each incoming information item will be analyzed, resulting in a set of structured representations about events, sub-events or actions, entities, relations, locations, time, and sentiments that are observable in that information item. These knowledge elements will be expressed in the AIDA common semantic representation.
- Either continuously or at set intervals, the AIDA prototype will generate all plausibly relevant hypotheses about the real-world situation, event, or trend that are supported by some interpretation of the input information items. These hypotheses must be differentiated by one or more significant knowledge elements, but may share subsets of knowledge elements.
- At any time during AIDA processing, both the whole knowledge base and the individual hypotheses will be available to the user for inspection and editing. The user will be able to adjust or downgrade the confidence of hypotheses postulated by the AIDA prototype or even add completely new hypotheses.
- Because of the processing carried out by the AIDA system, the user will have a complete, comprehensive, and nuanced view of an event, situation, or trend of interest. Knowledge derived from multiple media sources will be accessible to both users and automated analysis tools in a form that will enable them to find patterns, conflicts, or deception attempts that were previously imperceptible.
Check out these other hot stories: