Low Resource Languages for Emergent Incidents (LORELEI)

Abstract

The Low Resource Languages for Emergent Incidents (LORELEI) program developed technology to rapidly field machine translation and other language processing capabilities for low-resource foreign languages. The U.S. military operates globally, and frequently encounters low-resource languages, which are languages for which few linguists are available and automated human language technologies do not exist. Processing foreign language materials requires protracted effort, and current systems rely on huge, manually-translated, manually-transcribed, or manually-annotated data sets. As a result, systems currently exist only for languages in widespread use and in high demand. LORELEI took a different approach by leveraging language-universal resources, projecting from related-language resources, and fully exploiting a broad range of language-specific resources. The resulting capabilities can rapidly provide situational awareness based on information from low resource languages encountered during emergent missions such as humanitarian assistance/disaster relief, terrorist attack response, peacekeeping, and infectious disease response.

Document Details

Document Type
Accomplishment
Publication Date
Oct 01, 2022
Source ID
ee49ab06d81c0ddee2ed318fbb4b683d

Tags

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Emergency Management and Homeland Security.
  • Strategic Security Studies

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy
  • AI & ML - Machine Translation

Related Documents