 |
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.
|
|
 |
|
| |
|
| | USER - Home Page | USER - Projects | Computer Science - Home Page | | |
|
| Contact: | ||
| Rob Barrett | ||
| IBM Almaden Research Center | ||
| 650 Harry Road | ||
| San Jose, CA 95120-6099 | ||
| 408-927-1911 | ||
| e-mail: barrett@almaden.ibm.com | ||
|
|
[ Almaden
Research Center | IBM Research ]
[ IBM home page | Order | Search | Contact IBM | Help | (C) | (TM) ]
Last updated: Monday, 10-May-2004 14:00:23 PDT
