A Raytheon Technologies business will develop an end-to-end system designed to help intelligence community analysts extract mission-relevant semantic data under the Intelligence Advanced Research Projects Activity’s Better Extraction from Text Toward Enhanced Retrieval program.
The Cross-Lingual Extraction for Versatile and Effective Retrieval system to be developed by Raytheon Intelligence & Space could enable English-only speakers to search and retrieve documents from large volumes of foreign language data and could learn from queries and other activities of users, the company said Wednesday.
“For non-native speakers understanding context across languages is critical to extract the appropriate semantic information,” said Bonan Min, a Raytheon BBN scientist.
“With machine learning and artificial intelligence, we’re able to deliver the semantic information and search results that today’s intelligence analysts need,” added Min.
In 2019, IARPA selected Raytheon BBN and three universities to perform research and development work on the BETTER program.