The goal of the Babylon program is to develop rapid, two-way,
natural language speech translation interfaces and platforms for the
warfighter for use in field environments for force protection, refugee
processing, and medical triage. Babylon will focus on overcoming the
many technical and engineering challenges limiting current
multilingual translation technology to enable future full-domain,
unconstrained dialog translation in multiple environments.
The Babylon seedling project, “RMS,” or Rapid
Multilingual Support, was deployed to Afghanistan in the spring of
2002. The Babylon program will focus on low-population,
high-terrorist-risk languages that will not be supported by any
commercial enterprise. Mandarin and Arabic were selected based on
immediate and intermediate needs.
- FY 02: In direct support of field operations, Babylon will
build and rapidly deploy one-way speech translation systems for
four target languages: Pashto, Dari, Arabic, and Mandarin.
Systems will be delivered in the form of militarized palm-sized
PDA devices (12 hour battery endurance) that conform to the
military uniform ensemble.
- FY 02: Each of four Babylon two-way translation teams will
develop ten domain (task)-constrained, natural language
translation prototypes hosted on multiple platforms. Each system
will undergo an evaluation process and the successful teams will
advance and continue to refine their system through technology
patches and insertions.
- Follow-on years will expand the domains, or tasks, supported
by the Babylon prototypes, and improve their robustness and
responsiveness to field requirements.
- DARPA Babylon Site
- Charles Wayne, "Human Language Technology TIDES, EARS, Babylon" at DARPATech 2002
- EFF Mirror: Charles Wayne, "Human Language Technology TIDES, EARS, Babylon" at DARPATech 2002