DYNAMIC PAGE -- HIGHEST POSSIBLE CLASSIFICATION IS
TOP SECRET // SI / TK // REL TO USA AUS CAN GBR NZL
(S//SI) SID and RAD to Develop Lexicons in Five Languages
FROM: Dr. David Savignac
CAMT Technical Director (S21212)
Run Date: 04/09/2004
FROM: Dr. David Savignac
CAMT Technical Director (S21212)
(S//SI) Thanks to $500K of Intelligence Community funding forwarded by NSA's CounterBiological Weapons Program, SID's Center for Applied Machine Translation (CAMT) has begun to
create lexicons covering biological weapons terminology in five critical languages: Russian,
Chinese, Korean, Arabic, and Farsi. NSA's Counter-BW Program is jointly run by the Research
Associate Directorate (RAD) and the Office of Proliferation and Arms Control (S2G), and is
funded by the Intelligence Community's Intelligence Technology Innovation Center (ITIC).
(S//SI) ITIC had originally provided the funds to NSA to improve machine translation algorithms
for the biological weapons target, but in the course of discussions between
(RAD) and Dr. David Savignac (CAMT), it became clear that ITIC's requirement could be best
met by having the CAMT create appropriate lexicons in the target languages. ITIC concurred to
this modified approach and was pleased to learn that the CAMT believed that it could stretch the
money to cover lexicon development in more than the original five languages.
(S//SI) Once completed, the new lexical information will be immediately integrated into the
CAMT's CyberTrans machine translation software to improve automated translation capabilities
for this extremely important domain. The lexicons will also be provided to commercial machine
translation venders (Systran, Language Weaver and possibly others) for inclusion in software
which they supply to the US Government; they will also be released to field sites, training
institutions, and the relevant target offices.
(C) The CAMT's CyberTrans software is used throughout the Intelligence Community, the
Department of Defense, and 2nd and 3rd Parties to translate foreign language text from some
sixty languages into English. The biological warfare lexicon project will proceed under the
leadership of Dr. Carl Rubino of the CAMT, who is presently overseeing the creation of WMD
lexicons in Arabic, Turkish and Uzbek.
POC: Dr. Carl Rubino, CAMT/S21212,
@nsa,
"(U//FOUO) SIDtoday articles may not be republished or reposted outside NSANet
without the consent of S0121 (DL sid_comms)."
DYNAMIC PAGE -- HIGHEST POSSIBLE CLASSIFICATION IS
TOP SECRET // SI / TK // REL TO USA AUS CAN GBR NZL
DERIVED FROM: NSA/CSSM 1-52, DATED 08 JAN 2007 DECLASSIFY ON: 20320108