Using clustering and SuperConcepts within SMART: TREC 6

The SMART information retrieval project emphasizes completely automatic app roaches to the understanding and retrieval of large quantities of text. We continue our work in TREC 6, performing runs in the routing, ad hoc, and fo reign language environments, including cross-lingual runs. The major focus for TREC 6 is on trying to maintain the balance of the query - attempting t o ensure the various aspects of the original query are appropriately addres sed, especially while adding expansion terms. Exactly the same procedure is used for foreign language environments as for English; our tenet is that g od information retrieval techniques are more powerful than linguistic knowl edge. We also give an interesting I cross-lingual run, assuming that French and English are closely enough related so that a query in one language can be run directly on a collection in the other language by just 'correcting' the spelling of the query words. This is quite successful for most queries . (C) 1999 Elsevier Science Ltd. All rights reserved.