DARPA Unfamiliar Metadata Project

Research Summary


  • The objective of this project is to link ordinary language queries to unfamiliar indexes and classifications.

What's the problem

  • Databases quite often use idiosyncratic classifications and unfamiliar terminology in their indexes.
  • However, database users are often unfamiliar with terminologies and classification schemes of a database.
  • Therefore, database users sometimes experience difficulty choosing search terms that are actually used to index the database.

What we are trying to do

  • In this project, "Entry Vocabulary Modules" are built to respond adaptively to a searcher's query posed in ordinary language. This is accomplished by responding to the ordinary language query with a ranked list of terms that may more accurately represent what is sought as it is represented in the database of interest than the searcher's choice of terms.
  • The aim of "Entry Vocabulary Modules" is to facilitate a more direct connection between ordinary language queries and unfamiliar indexing terms actually used to organize information in a variety of unfamiliar databases.