AVENUE: Rapid development of machine translation for low density languages NSF

1
AVENUE Rapid development of machine translation
for low density languages (NSF)

• New Ideas
• Use machine learning to learn translation rules
  from native speakers who are not trained in
  linguistics or computer science.
• Multi-Engine translation architecture can
  flexibly take advantage of whatever resources are
  available.
• Research partnerships with indigenous communities
  in Latin America and Alaska (Mapudungun (Chile),
  Siona (Colombia), Inupiaq (Alaska), Quechua
  (Peru))

Interface for data elicitation

• Impact
• Rapid and low-cost development of machine
  translation for languages with scarce resources.
• Policy makers can get input from indigenous
  people.
• Indigenous people can participate in government
  and internet.

AVENUE-Mapudungun

• Joint effort with bilingual and multi-cultural
  education programs at the Chilean Ministry of
  Education and the Indigenous Studies Institute at
  Universidad de la Frontera.
• 80 hours of Mapudungun conversation recorded and
  transcribed. Currently being translated into
  Spanish.
• Plans for development of Machine Translation and
  Computer-Assisted Language Learning.

Carnegie Mellon University, Language Technologies
Institute Carbonell, Brown, Lafferty, Lavie,
Levin, Schultz, Waibel