Intelligence Value
Novel and low-frequency terms (e.g., newly coined slang, jargon, coded language and undefined acronyms) present a persistent challenge for the analysis of multilingual text and speech by analysts and data scientists. Language changes quickly and can be rapidly adapted to evade detection. Decipher will compress the discovery cycle by enabling the Intelligence Community (IC) to analyze communications containing complex or cryptic language, as well as triage large, multilingual collections of text and speech for mission-relevant information that otherwise eludes modern information retrieval (search) technology.
Summary:
The Decipher program’s goal is to create capabilities to detect specialized language of interest to a user and generate probable definitions for unfamiliar, coded and novel terms. Decipher will infer potential meanings from (often limited) contextual information and provide translation and annotation of specialized terms, including jargon, slang, and acronyms, in texts and speech. The program will also develop technology to annotate text with relevant social and contextual factors, capturing nuanced meaning, as well as to detect concept drift by monitoring use of terminology as it evolves over time.
