The initial impetus for the establishment of the Low Resource Human Language Technology (LoReHLT) evaluation was for LoReHLT to serve as a program evaluation for the Defense Advanced Research Projects Agency (DARPA) Low Resource Languages for Emergent Incidents (LORELEI) research program. As evaluation planning developed, however, NIST and DARPA decided to open the program evaluation to the rest of the national and international research communities, in order to encourage research progress in the LORELEI-related problem space. This article describes the motivation, concept of operations, and structure of the LORELEI Program to provide some background for the design decisions made within the LoReHLT evaluation.
This is a preview of subscription content, log in to check access.
Buy single article
Instant access to the full article PDF.
Price includes VAT for USA
Subscribe to journal
Immediate online access to all issues from 2019. Subscription will auto renew annually.
This is the net price. Taxes to be calculated in checkout.
The U.S. Department of Defense declares this article: Approved for Public Release. Unlimited Distribution.
About this article
Cite this article
Christianson, C., Duncan, J. & Onyshkevych, B. Overview of the DARPA LORELEI Program. Machine Translation 32, 3–9 (2018). https://doi.org/10.1007/s10590-017-9212-4
- Natural language processing
- Machine translation
- Humanitarian assistance
- Disaster relief