IBM Research - Almaden - User System Ergonomics Research

 FIRE -- Finding Information by Relevance Evaluation


  FIRE is a user-interface agent which helps a searcher refine an initial query. By simply indicating whether a found article is "relevant" or "trash", information is provided to this agent. This relevancy information enables the agent to suggest new search terms which will produce better query results.

Unlike many other relevance feedback systems, FIRE is designed to always keep the searcher in full control of the query. New search term suggestions are always offered to the searcher for approval and the searcher can ask the agent to explain why certain terms are being suggested. FIRE works smoothly with the normal flow of performing a textual query, requiring little additional input, and providing useful query refinement help.

Initial Query

Viewing Found Documents

FIRE Engine Analysis

Refined Query

  | USER - Home Page | USER - Projects | Computer Science - Home Page |
    Rob Barrett
    IBM Almaden Research Center
    650 Harry Road
    San Jose, CA 95120-6099

[ Almaden Research Center | IBM Research ]
IBM home page | Order | Search | Contact IBM | Help | (C) | (TM) ]

Last updated: Thursday, 21-Jul-2011 15:25:04 PDT