Machine Translation for English Retrieval of Information in Any Language (MATERIAL)

Program Manager

Carl Rubino

Program Information


MATERIAL Logo Final 150The MATERIAL Program seeks to develop methods for finding speech and text content in low-resource languages that is relevant to domain-contextualized English queries. Such methods must use minimal training data and be rapidly deployable to new languages and domains. Content that is responsive to the queries will be returned from multiple genres along with succinct summaries in English. The overall end-to-end capability will enable monolingual triage of multilingual datasets.

Performers (Prime Contractors)

Johns Hopkins University; Raytheon BBN Technologies; Columbia University and University of Southern California Information Sciences Institute

Related Program(s)


Research Area(s)
  • Natural language processing
  • Machine translation
  • Cross-lingual information retrieval
  • Domain recognition and adaptation
  • Multilingual ontologies
  • Multilingual speech recognition
  • Cross-lingual summarization
  • Keyword search algorithms
  • Low resource languages
  • Automatic language identification
  • Machine learning
  • Rapid adaptation to new languages
  • Domains and genres

Related Publications

To access MATERIAL program-related publications, please visit Google Scholar

Related Article(s)

Press Releases and Statements

IARPA Launches “MATERIAL” Program